Video unavailable. Open the source below.
NewJev Mail Classifier
Classify email into multiple categories and apply configured mailbox actions from Jev probabilities.
Explore Jev AI use cases and experiments through projects, X posts, and videos, including apps that call Jev in realtime or nearly. See how Jev works in real projects like Jev Ultrafast, Fast Jev Compaction, and Hermes Jev Skills.
Video unavailable. Open the source below.
NewClassify email into multiple categories and apply configured mailbox actions from Jev probabilities.
Video unavailable. Open the source below.
NewLabel visible X posts with typed Jev judgments about promotion, engagement prompts and information density.
A tool-running agent lets Jev choose actions and arguments from the current conversation.
Give agents typed Jev decisions with explicit screening and escalation to their host.
Filter lines and records with natural-language predicates and Jev probabilities.
Bind typed Jev questions to Ruby object fields for validation and routing.
A benchmark walkthrough compares thirteen decision models on quality, response time, question types and local hardware requirements.
A Hebrew walkthrough connects OpenClaw to Jev with a small triage plugin, waking the larger model only when needed.
A French technology and business podcast includes a segment on Jev’s adoption and reported revenue, alongside other industry topics.
Rank text on a natural-language criterion using pairwise Jev judgments and a fitted statistical scale.
Simulate a drone fleet whose Jev reflex decisions can use optional strategic advice from a slower model.
Fifteen practical recipes show how typed Jev answers drive routing, classification and evaluation.
Runnable typed-decision examples combine Jev judgments with thresholds and deterministic policy checks.
Supervise Hermes agent work with Jev decisions, evidence checks and explicit completion authority.
Select relevant coding-agent memories with independent Jev judgments instead of embeddings.
Control an everyday Chrome browser with typed Jev decisions and explicit safety checks.
Cole Medin demonstrates Jev decisions for email handling, prompt-injection checks, news filtering and duplicate detection.
A Chinese-framed lesson compares Jev, an ordinary language model and a distilled local model in Pac-Man, including the limits of task-specific training.
NeuralNine explains how Jev can speed up Hermes agents through typed decisions and hooks.
A comparison reports 505 graded decisions and demonstrates support routing and a phone assistant with Jev and OpenAI’s Decisions API.
Use Jev to filter and rerank retrieved passages before a Spring AI answer.
Filter and rerank retrieval candidates using typed Jev relevance judgments.
Classify Gmail messages with custom labels, confidence gates and a metadata-first Jev decision.
An agentic RAG walkthrough using Jev for routing, reranking and citation checks, with Langfuse traces.
A MotherDuck workshop showing five SQL text-classification use cases with Jev on real datasets.
A Spanish session demonstrating email classification with Jev and discussing speed, cost and use cases.
An explanation of Jev with examples of email sorting, SQL classification, browser control and agents.
A Portuguese discussion of typed decisions, Jev use cases and an open alternative.
A Portuguese review of Jev for coding workflows, including useful applications and model limitations.
A discussion of independent Jev benchmark results and the limits of decision models.
Jev chooses text, tables or interactive visuals before a chat model creates the answer.
Optional Jev checks filter and rerank memory cards for an agent workspace.
Jev checks codebase questions and retrieved passages before memory evidence is used.
Video unavailable. Open the source below.
NewRoutes jobs and handoffs among four Dots agents, with human approval for money and client actions.
A Georgian-language podcast discusses Jev as a fast classifier and its practical uses, then explores coding agents and verification.
A Korean overview places Jev beside Clef and Laya, then demonstrates the open models on email classification, flight screens, and electric-car data. The creator explicitly says Jev itself was not run.
Video unavailable. Open the source below.
NewSearches thousands of YC startups with flexible natural-language queries.
Checks new events against stored facts and records whether memories remain valid.
A browser extension combines Jev writing-style judgments with local rules to flag likely AI prose.
A browser extension uses typed decisions to choose actions from the current page.
Screens and ranks source files by a plain-language implementation goal.
A walkthrough builds a browser agent that combines Jev decisions with Claude reasoning and discusses where it fails.
A practical comparison tests Jev on customer messages and shell commands alongside small and frontier language models.
A technical overview compares the OpenAI Decisions API with Jev’s approach to structured decisions.
A Korean-language discussion distinguishes Jev decision models from LLMs and Dots agents.
A Portuguese-language comparison tests Jev and Clef on the same recommendation queries in a working application.
An Italian-language walkthrough applies Jev to message routing and lead classification, with discussion of its limits.
A Spanish-language introduction explains System One models and how to use fast typed decisions.
Diogo Almeida discusses calibrated decisions, RLCD and how Jev can fit into software and agent architectures.
A Korean-language overview compares Jev and the OpenAI Decisions API for structured decisions and inference cost.
John Lindquist demonstrates typed decisions for speech, documents and live data, then discusses failure cases and question design.
Jev ranks Apple documentation and WWDC transcript matches after hybrid retrieval.
Video unavailable. Open the source below.
NewJev selects traffic-light phases in a city-grid simulation.
A Tamil-language tutorial explores Jev with retrieval-augmented workflows, from connecting data to using retrieved evidence.
A walkthrough builds a support inbox sorter, prompt checker, podcast clip finder, and job matcher with Jev and Claude Code.
A Vietnamese-language guide explains Jev’s typed questions, confidence, suitable uses, limitations, and practical examples.
A Portuguese-language explanation introduces OpenAI’s Decisions API and compares its approach with Jev.
An Italian-language comparison discusses benchmark tests across Jev, Laya, Rizzo Flow, and another language model.
A Korean-language introduction tests Jev, explains its decision-focused design, and discusses its limitations.
Jev scores prompt injection and proposed shell commands before coding-agent hooks allow them.
An introduction to Jev’s architecture and how its decision-focused design differs from conversational models when building AI applications.
A tutorial presents a Jev-assisted video-editing workflow and discusses the creator’s approach to using decision models in editing.
A practical guide to Jev’s decision types and four design patterns, combining them in a customer-support workflow.
An explanation of Jev and System One models, covering typed decisions, calibration, latency, cost, and the trade-offs of decision-focused AI.
An AI news roundup includes a Jev segment covering TypeSafe’s decision model, alongside other model and tooling announcements.
A developer discusses how Jev could change the way AI is used in applications, with a review of its decision-focused approach.
A Japanese podcast discusses Jev’s role in software alongside coding agents and other AI tools. Its Jev segment starts at 1:20:43.
A Chinese comparison tests Claude Code with and without Jev on feedback, document classification, and billing checks. It discusses matching results and the corrections needed.
An Indonesian tutorial demonstrates Jev in customer support and online shopping, including an OpenRouter integration and application deployment.
A Portuguese tutorial demonstrates adding Jev to Claude Code modes and shares the prompts used for the integration.
A developer-focused introduction to Jev, its typed decisions, and practical ideas for using it inside applications.
A Spanish review questions the rush to adopt System One models and explains why the creator chose not to integrate Jev into gentle-ai.
A Korean overview explains Jev’s decision outputs and discusses how lower inference costs could expand the use of AI inside software.
A Portuguese walkthrough connects Jev to a Claude Code dashboard, then uses store data to assess likely causes, risks, and possible actions.
A hands-on comparison of OpenAI’s Decisions API and Jev, using image inspection, outage investigation, and report checks to compare capabilities, response time, and cost.
Classify text columns with typed Jev decisions directly in SQL.
Video unavailable. Open the source below.
NewA browser extension uses Jev to map ambiguous form labels to saved personal-profile fields.
Video unavailable. Open the source below.
NewPermission-aware document-tree retrieval with Jev branch routing and passage scoring.
A creator demo of using Jev to identify sensitive-looking paths in a file share.
A creator demo of a Jev gate before a model pass, with visible routing outcomes.
An optional Jev tool gives a local document agent typed classification, routing, and scoring decisions while the caller keeps thresholds and execution policy.
The DuckDB extension passes each ticket row's body text and constant criteria to jev_ask.
Tasksource publishes rows with state, question, kind, options, and target.
For a semantic tool-action check, the plugin sends a redacted state containing the current task, applicable rules, and proposed action.
Each isEven(number) call sends the number as state and asks a Choice question keyed category with true and false criteria.
Jev classifies the operator’s text into query, diagnosis, action, or chat.
The controller first asks Jev to select a manipulation intent from the task and observed geometry facts.
For each T-Rex game decision, a deterministic physics planner creates a text state and labels jump, duck, and run as safe or unsafe under the model’s answer timing.
For a message and optional recent context, Jev receives two questions in one request: intent Choice and direct-reply-risk Score.
When the TypeSafe classifier is selected, Sharp sends a Noul question asking whether to hide each eligible X post under the reader’s plain-language filter instruction.
For each article, the client sends a state containing the title and up to 4,000 characters of body.
The query analyzer sends the user's log query and known service names to Jev.
For each new message, Jev sees the latest message, recent conversation, available recent results, and any pending question or confirmation.
Video unavailable. Open the source below.
NewThe demo sends measured browser state, the goal, and recent action history to a typed Choice question for the next browser action.
The plugin sends numbered source snippets as state.
Jev reads the assistant instructions and recent conversation turns, then answers a typed tool Choice and a Noul question about whether a tool call is needed.
pijev sends the same ticket state with several typed Choice questions that vary only the order of the same support-team criteria.
A German-language demo uses Jev to classify 23 synthetic real-estate inbox messages, then examines corrections and failure cases.
Better Stack compare Jev and Clef on 200 channel comments with an LLM referee, then test Clef on thumbnails. The reported accuracy, price, and speed results are specific to this creator experiment.
IndyDevDan discusses model usage and an explicit Jev System One segment, including his reported experience adding Jev to a Pi agent. Market and savings claims are the creator’s commentary.
A French discussion explores decision models, agent oversight, industrial automation, and fatigue from approving agent actions. The episode presents the speakers’ views.
The AI Automators compare next-tool decisions on 1,000 support conversations and discuss richer state, fine-tuning, confidence, and calibration. Reported results depend on the creator’s task and test split.
A Portuguese tutorial explains typed decisions and OpenRouter setup, then compares Jev with Claude Haiku on 100 channel comments. Speed and cost results are the creator’s reported experiment.
A CLI for testing authored Jev questions against labeled examples, selecting thresholds, measuring calibration, and checking changes against held-out data.
A benchmark harness that compares Jev and DeepSeek on comment-labeling tasks and records per-item outcomes, usage, cost, and latency.
An SRE agent evaluation framework with optional Jev decision support for reviewing diagnostic plans and submitted evidence.
A research and trading workbench with a Jev-powered futures monitoring and proposal-evaluation path connected to a simulated contest account.
A terminal app whose command palette combines local fuzzy matching with optional Jev ranking of commands, tabs, and sessions for plain-language searches.
A Chrome side panel that maps a user request to page-provided WebMCP tools and their typed arguments using Jev.
A ranking tool that uses pairwise model comparisons across batches and repeated trials to find the strongest items in a large collection.
A browser-agent extension that combines language-model planning with Jev-selected browser actions and an evidence-checked execution runtime.
A local OpenAI-compatible proxy that caches repeat model requests and can use Jev to judge safe semantic reuse after exact cache misses.
A computer-use action layer that lets an agent hand bounded desktop subtasks to a fast decision model for execution.
A coding-agent permissions plugin that uses Jev to review unresolved shell approval requests.
An Obsidian plugin for multi-provider chat, workflows, and local vault search, with optional Jev filtering for retrieved results.
A JMeter plugin that adds AI chat and Agent Mode, with optional Jev routing to select a focused tool pack for a request.
Video unavailable. Open the source below.
NewAn agent workspace that routes plain-English requests to specialist agents, skills, and workflows, including an optional Jev-powered route.
A command-line toolkit for agent handoffs, workspace context, and developer workflows, with optional Jev decisions for routing and checks.
A browser automation skill that uses page-observed controls and Jev choices to carry out and verify user goals.
An FkWeChat plugin that classifies a selected message's intent, emotion, urgency, and suggested reply posture.
A Jev decision layer for DeepSeek Harness and other MCP hosts, with explicit controls for provider use and data egress.
A Portuguese lesson on System One decisions, including WhatsApp routing, form completion, data migration and judging generated writing.
Maestros da IA walks through a Jev Voice experiment, including transcription, model routing, batched typed questions, voice-triggered tasks, and live concept and fact checks. The original title and description are Portuguese, while the API…
Simone Rizzo explains a contrasting decision-model approach and compares it with Jev. The creator presents its speed claim; this listing does not independently verify that benchmark.
CoderOne reviews Clef as an open decision-model alternative to Jev, discusses benchmarks, and demonstrates its local webcam and playground workflows.
A research reading workflow that uses Jev to rank candidate papers by relevance before an agent writes commentary and notes.
An opt-in Claude Code mod in Treg remembers lasting project preferences from answered prompts using Jev.
Quivr V2 combines durable stream ingestion with natural-language article alerts judged by an optional Jev classifier.
A PostgreSQL extension and workspace provide natural-language SQL planning, semantic operators, reusable evidence, and reviewed query execution using Jev judgments.
An Android chat client optionally uses Jev to screen memories for relevance and expose a judge tool to its main model.
A financial decision harness compares deterministic rules with optional Jev typed judgments over fixed evidence cases.
An Android conversation assistant reads the visible chat, asks Jev for structured judgments, drafts reply candidates with a text model, then uses Jev to rank them for the person to review.
An agent platform exposes typed Jev decisions through a UI, an agent tool, and a System One-compatible API, with local and hosted backends.
Perch scans code and dependency graphs with configurable System One models, including Jev, to assess issues and rank findings.
A transcript summarizer can optionally use Jev to prefilter relevant passages before the existing summary model runs.
A local document workflow uses Jev to classify document pages and identify document boundaries, with review for uncertain results.
Video unavailable. Open the source below.
NewA VS Code debugging extension uses Jev to route each debugging step, with a language model available as a baseline or for other tasks.
A local astrology skill offers an optional TypeSafe Jev decision layer for narrow routing and interpretation judgments.
A Playwright-based browser skill lets an agent run a bounded web task while Jev selects page actions.
A creator demo uses one 24-way Jev Choice per AI paper to build a searchable topic map, then separately evaluates the labels with Opus.
A model-agnostic metacognition loop that generates candidate reasoning paths and uses a System One judge such as Jev to select or score them.
Research workflow skills for CNKI that include an opt-in Jev extension for title and abstract screening proposals.
A collection of agent skills and tooling that includes a CLI classifier with Jev and Pi classifier transports.
An agent runtime can ask Jev to answer narrow error-classification questions before using the main model.
Video unavailable. Open the source below.
NewAn agent runtime optionally uses Jev to select relevant memories and detect explicit dismissal of saved lessons.
A token-saving context compactor that uses Jev Noul judgments to choose which tool calls and results to retain.
Open source project with an optional OpenCode tool that lets an agent ask Jev for a structured choice.
A Codex hook that asks Jev to choose GPT-6 reasoning effort and how many generations to keep that choice.
A local Apple Silicon browser agent port of jev-ultrafast that uses Laya typed decisions by default and retains hosted Jev as an optional mode.
A Bitcoin trading demo that sends a compact technical-indicator snapshot to Jev for typed market judgments, then applies confidence and risk controls before reporting a position.
The creator presents Arabic-language Jev decision-model explanation. Reported performance and product claims are not independently reproduced.
A substantial tutorial explains a Jev decision layer alongside Claude implementation work.
An end-to-end explanation of Jev, Choice, Score and Noul, with model routing and confidence-gated workflows.
A tutorial surveys 19 workflows that combine Jev decisions with Claude generation.
A Korean-language report compares Jev with the open-source Laya decision model and reviews its licensing.
A long-form tutorial introduces Jev-style decision models and builds an independent model, decision head and training dataset.
A demo contrasts generated candidate decisions with the subset used, showing a speculative Jev decision workflow.
A Jev app gives an AI estimate of how a proposed X post might be received from a girlfriend's perspective.
Video unavailable. Open the source below.
NewA human plays Speed against a Jev opponent, with judgment confidence, latency and rule-validation panels.
Video unavailable. Open the source below.
NewThe example pairs local tokenization with Jev-generated language and lint annotations in a small developer tool.
Video unavailable. Open the source below.
NewIt combines content review with engagement ratios to help a reader screen a short feed around a selected niche.
Video unavailable. Open the source below.
NewIt puts Jev in a software review decision flow, turning a PR link into a merge-or-review recommendation.
Video unavailable. Open the source below.
NewThis is a concrete batch classification example: Jev selects among a fixed set of 24 research topics after another model compresses each paper into a summary.
Video unavailable. Open the source below.
NewIt applies Jev to an in-the-moment sales workflow where the output is contextual guidance during a conversation, rather than a post-call summary.
The project turns a single probabilistic request into a varied exploration grid by combining independent slot distributions, enforcing incompatibility rules, and selecting diverse combinations.
The examples make the boundary between classification and action concrete: Jev supplies typed probabilities, while ordinary application code applies thresholds, confidence checks, and human-review branches.
The adapter lets a typed classifier choose among a game's existing actions while enforcing that the answer is one of the offered options and has the highest reported probability.
The integration narrows model judgment to candidate selection over source-checked records, with privacy checks, input and question budgets, caching, deadlines, and a local fallback around the call.
It makes typed probabilistic classification an optional primitive inside a sandboxed tool-calling agent.
It combines market microstructure with stratified social evidence in one structured decision request, with separate typed outputs for recommendation, sentiment, squeeze risk and news impact.
It evaluates agent behavior with a fixed set of interpretable metrics plus action-window questions, while minimizing or explicitly confirming session data before sending.
Typed judgments are combined with explicit product rules: a cautious Noul threshold protects legitimate bold copy, while score/archetype weights adapt to text length.
The state keeps the search intent beside each candidate result, while the same judgment API supports individual calls and batched per-result decisions to limit round trips.
Rules are declared as typed choices over compiler-like Rust contexts, so teams can tailor checks while dry-run exposes the exact planned state and request before the API call.
It adds a typed review layer to deterministic malware signatures: the model sees the exact matched text and surrounding source, while the existing scanner remains the source of detections.
The decision input is constrained to task-relevant candidate fields, candidate IDs are remapped before sending, and abstention is an explicit option when the evidence does not distinguish a suitable assignee.
The example shows both direct multi-type classification and Jev as a router classifier, with an explicit minimum-confidence setting before dispatching to a selected model.
It packages Jev evaluation behind a provider interface and exposes inspectable typed-request examples, so an API caller can switch among TypeSafe and other evaluation providers while keeping the same state-and-questions contract.
It makes a structured decision model usable through an existing chat-completion API by translating schema fields into typed decisions, while retaining Jev probabilities and confidence in the original response metadata.
Video unavailable. Open the source below.
NewThe same typed-decision model supports a complete project-memory loop: classify and filter completed turns, retrieve memories for the next prompt, and evaluate relevant safety rules before tool use.
A walkthrough of fourteen knowledge-work applications for Jev, including inbox triage, document classification, lead scoring and evaluation with Notion workflows.
An interview with TypeSafe founder Diogo Almeida about probabilistic software, reliable decisions and embedding intelligence inside applications.
An explanation of the encoder architecture behind Jev and how its decision workload differs from autoregressive text generation.
A practical explanation of Choice, Score and Noul through a voice-controlled canvas and a scripted World of Warcraft agent, including the demos’ limits.
A Portuguese introduction to Jev typed decisions with demonstrations of using the model through OpenRouter and the Overclock coding workflow.
A Portuguese walkthrough of Jev model and effort routing for Claude Code, comparing a proxy approach with a native plugin and demonstrating the workflow.
A practical explanation of Jev state and typed questions, with a decision lab comparing models and discussing calibration and application limits.
A short explanation of what is new about Jev and how it compares with classifiers and large language models.
Video unavailable. Open the source below.
NewA creator-posted trading experiment shows an autonomous multi-agent dashboard and market activity.
A security recon framework applies bounded Jev decisions to page classification and scan planning.
A multi-source news monitor assesses reader value using a structured Jev rubric.
A Korean comparison discusses Laya as an open-source alternative to Jev.
A Mandarin introduction explains Jev’s decision-only behavior and contrasts it with conversational assistants.
A Chinese-language DevDay commentary compares decision-oriented AI products with Jev and Grok.
A Portuguese comparison explores Laya as an open-source alternative to Jev for decision tasks.
A Portuguese overview compares Jev decision models with text-generating models in software architecture.
A Portuguese introduction covers the playground, response types, BANT lead scoring and community projects.
Ten practical patterns progress from typed if statements to routing, confidence gates, file reads and agent integration.
A Japanese walkthrough discusses Jev design and adding the decision model to an agent.
Martin Keen explains System One decisions, probabilities, calibration, guardrails and how Jev complements language models.
Video unavailable. Open the source below.
NewAn animated folder interface automatically displays tags for documents.
Video unavailable. Open the source below.
NewAn audio drop routes language detection, transcription, privacy and task extraction through local models.
A crawler combines deterministic technical checks with typed semantic judgments for actionable SEO reports.
An input field turns natural language into structured interface cards through parallel typed decisions.
An optional browser-control fast lane uses Jev to choose operations and UI targets.
A research agent evaluates report relevance, evidence and citations with a strict Jev decision adapter.
A distillation CLI uses hosted Jev teacher judgments to label data for a smaller local classifier.
Video unavailable. Open the source below.
NewA playful emoji interface responds to text queries while selected emoji rise from a pile.
Video unavailable. Open the source below.
NewA playful X feed renders posts in animated game consoles, robots and retro televisions.
Video unavailable. Open the source below.
NewA bookmark-informed policy sorts an X feed into Hide, Skim and Keep decisions.
Video unavailable. Open the source below.
NewA real Android end-to-end test compares Jev and DeepSeek navigation on the same fifteen-step Wikipedia task.
Video unavailable. Open the source below.
NewA live League of Legends overlay estimates the winning team, player impact and throw risk.
Video unavailable. Open the source below.
NewA coding workflow separates cached decisions, safe defaults and user questions from Opus implementation work.
A Cloudflare site search reranks Go proposal articles with Jev relatedness judgments.
Video unavailable. Open the source below.
NewA cube race compares Jev, Laya, GPT and Opus under the same move and time limits.
Video unavailable. Open the source below.
NewTwo models play the same Tetris piece sequence while a live dashboard compares outcomes and response times.
A presentation builder uses Jev to score slide-to-layout fit while deterministic assignment enforces layout constraints.
An API gateway forwards native Jev System One requests with account isolation, usage billing and bounded account failover.
A community plugin adds typed Jev decisions to DeepSeek Harness skill selection, file ranking, supervision and tool-output handling.
The creator presents n8n workflow routing with typed Jev questions. Reported performance and product claims are not independently reproduced.
The creator presents commentary on Jev computer-use and community demos. Reported performance and product claims are not independently reproduced.
The creator presents Jev usage walkthrough. Reported performance and product claims are not independently reproduced.
The creator presents eight practical Jev use cases in a developer interview. Reported performance and product claims are not independently reproduced.
The creator presents four concrete Jev coding workflows. Reported performance and product claims are not independently reproduced.
The creator presents three Jev integrations for Claude Code. Reported performance and product claims are not independently reproduced.
A Claude Code orchestration plugin compares typed Jev judgments with existing heuristics through opt-in shadow calls.
Video unavailable. Open the source below.
NewJev chooses context, worker routing, tool recovery and focused checks from host-prepared options while Opus handles reasoning.
Video unavailable. Open the source below.
NewJev forecasts booking outcomes from structured receptionist-call traces and answers five post-call questions.
Video unavailable. Open the source below.
NewJev classifies arriving headlines as bullish or bearish with confidence for a trading strategy built with Opus 5.5.
Video unavailable. Open the source below.
NewJev selects design parameters when a section enters view; Opus 5.5 writes the section and the app transitions to it.
Jev separates new buy or hold calls from brags, exits and news in crypto creators' posts; the app grades the resulting calls against BTC.
A support-ticket lab shows a Jev request, its typed response and integration with an LLM.
A walkthrough shows the architecture of a Claude and Jev agent workspace.
An Arabic explanation compares Jev decision calls with generative LLM work.
An overview surveys six practical Jev use-case categories and the model’s limits.
A walkthrough combines Claude with Jev in an agent workspace; savings are creator claims.
A technical walkthrough adds Jev decision calls to an agent harness.
A racing demo compares Jev and d1 lane choices on the same road.
A Jev adapter chooses presentation controls and scores candidate fit for a mobile assistant.
Jev chooses responders for unmentioned messages in an Auto-mode bot room.
A social research example routes user questions to evidence collection before generating an answer.
Coding-agent hooks use Jev to judge project rules and completion claims.
A live Jev controller chooses movement, view, fire, and interaction controls for DOOM.
Jev judgments help an agent guard allow, ask, or deny tool actions.
Benchmark Heaven compares Jev and other decision models on bounded decision tasks.
OpenRouter uses Jev to select a model and reasoning effort for each incoming request.
Video unavailable. Open the source below.
NewA creator demo pairs Opus-built option sets with repeated Jev decisions inside a research loop.
Video unavailable. Open the source below.
NewA hackathon ecosystem demo lets AI agents hunt, compete and survive to generate behavioral data.
Video unavailable. Open the source below.
NewA Minecraft server invites players to compete against a Jev-controlled opponent.
Video unavailable. Open the source below.
NewA creator-posted demo uses Jev to categorize financial transactions.
An interview and demo session explores using Jev for practical classification and agent decisions.
An overview explores Jev use cases for agents and code-based automation.
A developer walkthrough explains typed Jev decisions with application examples.
A Portuguese walkthrough presents Jev app ideas, example code and a business-building workflow.
A technical walkthrough compares TypeSafe Jev with local Laya and Kev decision models.
A macOS voice and text controller that selects live UI actions with Jev.
A logistics dashboard whose design system Jev selects from a one-sentence style brief.
A Korean-language walkthrough of Jev, its typed decision model and reported speed and cost claims.
A creator tests ten Jev use cases and discusses which claims held up in the demonstrations.
An English-language explanation of Jev’s role as a typed decision model.
A Japanese-language discussion of Perplexity, Aqua Voice and Jev in everyday work.
A long Japanese-language tutorial about Jev and decision-focused AI.
A code search CLI that asks Jev typed relevance and scope questions about candidate source blocks.
Tests Jev as a typed relevance judge and query router inside a RAG-Fusion retrieval experiment.
Runs typed Jev judgments over selected traces and spans in a user-triggered Instant Eval job.
A Spanish-language comparison of Jev with the open-source Laya alternative.
Laravel AI SDK classification gateway with a TypeSafe provider that sends typed Boolean, Choice, and Score questions to Jev.
Recorded xArm7 MuJoCo pick-and-place trial comparing Jev with two language-model controllers under the same Cartesian action interface.
PDF page router that uses Jev to identify pages needing OCR, extracts text pages locally, and merges the results in order.
Swift bridge that turns Apple Foundation Models @Generable schemas into Jev typed questions and reconstructs typed results.
Native Zig coding agent with an optional Jev-backed automatic permission reviewer for pending tool actions.
Semantic code search and diff linting that asks Jev whether source chunks match a behavior described in plain language.
A Korean-language tutorial shows Jev classifying customer inquiries before a person reviews which replies need a GPT-written draft.
A Malayalam-language explainer introduces Jev and discusses model routing, task prioritization, and ticket classification as possible uses.
An introduction to Jev decisions and calibration, followed by a Papers, Please-style approval-queue demonstration.
A beginner overview of the Jev model, its typed decisions and possible roles in agent workflows.
Andrew Warner surveys Jev uses such as email triage, model routing, support-ticket classification and agent-memory search.
A visual tour of a large collection of Jev demos and a head-to-head example.
A short explanation of Jev as a choice and probability model for bounded software decisions.
macOS chat overlay that judges incoming-message intent and reply risk, then ranks suggested replies.
Agent tool and CLI that batches typed Jev classifications, checks, scores and rankings for coding tasks.
Runnable PR-review lab that compares Jev and an LLM on candidate code-review findings.
Coding-agent fork with a native TypeSafe Jev judgment provider used for bounded agent decisions.
LLM gateway whose optional Jev complexity classifier routes each incoming request to a configured model tier.
EPUB translation tool that can ask Jev which markup groups contain text worth translating.
Agent platform that uses Jev to choose tools and browser actions.
Coding-agent workflow with optional Jev hints for correction detection and command risk.
Local MCP computer-use agent that lets Jev choose browser and macOS actions from observed controls.
Research agent that scores scraped passages with Jev before drafting cited reports.
A Claude Code module that uses Jev to route model tier, reasoning effort, and risky-action judgment for agent tasks.
A research Clash Royale bot that uses computer vision and Jev to choose gameplay actions on a real Android device.
A local proxy and live visualizer for Jev decisions and their conditional follow-ups.
A Mac WeChat reading and reply-drafting companion with optional Jev strategy selection.
A set of Jev-powered tools for Claude Code, including guarded tool calls, document classification, search, browser control, and review.
A demonstration of three AI trading bots whose decisions the creator says are made by Jev; trading claims are not independently verified.
A detailed Jev tutorial covering typed questions, routing patterns, and a customer-support triage build.
A Japanese-language practical review of Jev, including data organization, coding decisions, and limitations.
A Japanese-language explanation of how Jev returns decisions without writing prose.
A Chinese-language discussion of the TypeSafe founder’s arguments about RLHF and automation.
A survey of eight Jev applications, including filtering, email priority, search, and creative choices.
A technical explanation of Jev classifier architecture, use cases, costs, and limitations.
Researches a local document collection with Jev-backed evidence selection and coverage checks.
A walkthrough of running a Jev-style local decision model and the privacy tradeoff with cloud Jev.
An introductory explanation of Jev as a System One model and how typed decisions differ from chat models.
A trading-bot demonstration where Jev makes bounded decisions; results and strategy claims remain the creator’s.
A Japanese-language test of Jev against a trained game agent, including failures on other tasks.
A Spanish-language Jev tutorial with an email-classification example and use cases.
A creator walkthrough of building with Jev and placing typed decisions in an app.
A report surveying Jev experiments and applications, including driving and interface demos.
A comparison of Jev and Laya as decision models and the surrounding release discussion.
An Italian-language overview of Jev and its intended decision-model use.
A Jev introduction explaining how to use a decision-only model in application workflows.
A Jev analysis with a small local reproduction experiment and its limits.
A Python tutorial installing Jev and testing a small typed-decision program.
A setup walkthrough combining Jev, Claude, and computer-use examples.
A four-minute Portuguese-language explanation of the TypeSafe Jev decision model.
Video unavailable. Open the source below.
NewAdds a Jev decision to Command Code agent continuation.
Video unavailable. Open the source below.
NewA browser extension routes typed requests to page WebMCP tools.
Video unavailable. Open the source below.
NewChanges coding-agent reasoning effort during a task.
Video unavailable. Open the source below.
NewPairs streaming speech recognition with typed reading-error checks.
Filters creator clip ideas before rendering with Picsart.
Video unavailable. Open the source below.
NewAnalyzes early user journeys to find likely churn and product issues.
Chooses which tests are likely affected by a Git diff.
Grades text against rules using Jev judgments for each line.
Uses fast decisions to organize memory and guide retrieval for long-running agents.
Sifts synthetic and pretraining datasets with typed Jev decisions.
A desktop AI assistant with an inline Jev System One plugin.
A PHP AI framework with a typed Jev classifier integration.
A provider proxy for coding agents with optional Jev model and effort routing.
Builds animated math explanations and uses Jev to evaluate teaching and visual checkpoints.
A collaborative workspace that routes team conversations and review work to AI agents.
An explainer covers how Jev differs from generative models and where its typed decisions fit in real applications.
A long-form X video discusses Jev and its role as a fast typed-decision model.
A Hindi-language walkthrough explains Jev and demonstrates how to use TypeSafe AI’s decision model.
A longer explainer examines Jev’s decision-only interface and where it fits beside generative models.
A Spanish-language news discussion considers how a fast decision model could change automation workflows.
A practical overview discusses using Jev for bounded decisions alongside Claude’s generative work.
A beginner tutorial walks through Jev setup and example typed-decision calls.
A short video about Jev: Top 3 utilizzi di Jev in Claude Code.
A coding walkthrough builds a router using Jev and an open decision-model alternative.
A seventeen-minute coding explainer shows Jev’s typed decisions and how an application can call them.
A hands-on tutorial introduces Jev’s decision API and links example code.
An explainer discusses Jev’s non-generative decision interface and how it differs from a chatbot.
An Italian-language guide demonstrates Jev in a coding-agent workflow.
A French-language news video discusses Jev’s probability-based decisions and possible software uses.
An MCP proxy and hooks adapter screen agent tool calls and returned content with probability-based Jev judgments.
A small Grok Bot router uses Jev to decide whether to reuse work, stop retries, limit research, or ask for approval.
Video unavailable. Open the source below.
NewA playable Codenames experiment puts Jev in the game; the public post does not show the call.
Video unavailable. Open the source below.
NewA construction document pipeline classifies sheets before turning plan sets into bills of materials.
Video unavailable. Open the source below.
NewJev chooses Mario’s moves from structured game state; after death, four VM branches try different recoveries.
Video unavailable. Open the source below.
NewA Doom agent tries parallel futures from one checkpoint, compares outcomes, and continues from the best branch.
Video unavailable. Open the source below.
NewA form changes its next question dynamically instead of relying on a large fixed if/then tree.
Video unavailable. Open the source below.
NewSeveral Jev-controlled players attempt to play and negotiate in a forked Catan game.
Video unavailable. Open the source below.
NewA story game keeps a city on a whale alive through Jev-selected actions and generated video scenes.
Video unavailable. Open the source below.
NewA rover simulation changes litter-picking targets when its instruction changes from cans to bottles.
Video unavailable. Open the source below.
NewA prompt composer classifies task difficulty when the user finishes typing and offers a faster mode for simple requests.
Video unavailable. Open the source below.
NewA 3D character reacts during conversation with live choices for its face, gaze, and body.
Video unavailable. Open the source below.
NewA natural-language API finder uses Jev to choose among more than a thousand endpoints across dozens of providers.
Video unavailable. Open the source below.
NewAn agent-facing people search combines a broad provider search with Jev judgments about which leads match a user's criteria.
Video unavailable. Open the source below.
NewAn NFT listing scout uses Jev to reject weak opportunities and surface rare items for a personalized daily digest.
A MoonBit playground puts Jev's typed decisions into games, command-line experiments, browser actions, and agent safety checks.
Video unavailable. Open the source below.
NewA browser agent lets an LLM set the goal while Jev chooses page actions and checks progress in a Playwright loop.
A Pi coding-agent extension uses Jev to discover relevant tools and skills, make typed judgments, and optionally guard tool calls and compaction.
Search 6,241 Y Combinator companies by meaning, logo, visible text or tags, then have Jev score the shortlist.
A German-language walkthrough of ten Jev use cases and where typed decisions fit into automation.
A Chinese-language tour of Jev projects with a rabbit adventure and an alien-arrival decision demo.
The creator tests Jev 662 times on two Kaggle datasets and discusses surprising accuracy results.
A Portuguese-language explanation of five ways to place Jev decisions inside agent workflows.
An English introduction to Jev’s typed responses, speed, cost, and limits compared with an LLM.
A comparison-oriented overview of an open-source Jev-compatible decision model.
A Unix CLI that turns Jev judgments into predicates, routes, scores, filtered streams and stable exit codes.
Jev completed the Strongarm mission in original StarCraft shareware using structured state and mouse-and-keyboard actions.
A fail-closed permission gate for Pi that asks Jev to judge tool calls left undecided by hard rules.
Video unavailable. Open the source below.
NewA demonstrated Obsidian workflow that assigns tags to notes using Jev.
Video unavailable. Open the source below.
NewA visual builder that wires Jev Choice, Score and Boolean decisions into prompt workflows.
Daily rankings of agent skills across registries, with Jev judging social relevance, listing quality and category.
An opt-in Jev review of ambiguous dead-code findings in the Skylos scanner, with uncertain results left visible.
A creator demonstrates Jev and Treg across fraud screening, sales-signal triage and viral-content monitoring; reported savings are creator claims.
A five-minute explainer on why Jev returns fast structured judgments instead of generating prose, with discussion of its speed, cost and reliability claims.
A hands-on critique tests Jev for email sorting, comments, model routing and skill choice, then weighs where typed schemas help or constrain it.
A French-language review tests email, fraud-message and proposal triage, compares Jev with LLMs, and explains a confidence cutoff.
A Chinese-language tutorial demonstrates Choice, Noul and Score, then wires Jev into Codex for Gmail screening.
LangChain explains Jev's typed questions and demonstrates model routing, tool-risk decisions and online evaluation in an agent harness.
A long-form interview with TypeSafe's founder about System One models, calibrated decisions, RLCD and the limits of chat-first AI.
Two Minute Papers examines Jev's decision-model design and compares it with related models and research rather than relying on launch claims alone.
A Portuguese-language walkthrough places Jev between coding agents and their tool choices, with creator-reported benchmark limits.
Turing Post tests the Jev playground and a Codex workflow while explaining RLCD and asking where fast classification helps larger tasks.
A phone conversation copilot that reads visible chat and offers suggested replies while the user stays in control.
LLM-authored task-specific Jev harnesses with optional full-trajectory reward reflection and GEPA evolution.
Left-pad strings with TypeSafe AI's Jev. For reasons.
Zachi demonstrates a PostgreSQL extension that uses Jev to judge natural-language conditions across database rows without a vector index.
Moritz Kremb explains Jev, walks through API setup, and demonstrates voice-browser, memory, and YouTube-prediction applications.
An open-source JEV-powered workbench for streaming data selection, quality evaluation, automatic LoRA training and held-out model evaluation.
Jev, konuşan değil karar veren yeni bir yapay zeka modeli. TypeSafe AI'ın System One sınıfından ilk model. Metin üretmiyor, milisaniyeler içinde tipli kararlar döndürüyor. Bu Türkçe rehberde Jev'in ne olduğunu anlattım ve 3 canlı örnekle t…
The open versions of Jev are here . In this video we go through 7 of the open Jev style models to see how good they are and what they can do. Thanks to Dell for Sponsoring the Compute #DellProPrecision #DellProMax #DellTech #NVIDIA JevBenc…
TypeSafe AI has unveiled Jev, an AI model built to talk to software instead of people — returning typed, structured decisions instead of natural language, according to The Register. The startup, which raised $40 million and is led by forme…
Jev is TypeSafe AI’s new System One model. Instead of generating text, it makes fast, structured decisions and returns probabilities that software can act on. We’re now testing Jev inside the agent. In this video, I cover: - The idea behin…
Jev es un nuevo modelo de IA desarrollado por la empresa TypeSafe AI, este modelo está diseñado para tomar decisiones probabilísticas brindando una respuesta estructurada, en lugar de generación de texto como los LLMs. En este video te mue…
JEV from TypeSafe AI can fix the reranker in RAG 🔗 Helpful Resources & Links: Blogpost: Colab: If you found this breakdown helpful,
Aprenda Inteligência Artificial! ▸ Aprenda Agentes iA: ▸ Seja MEMBRO: ▸ ▸ Instagram:
In this video, I’ll be showing you how developers are using Jev, TypeSafe AI’s fast decision model, for browser automation, coding agents, context compaction, model routing, skill selection, semantic SQL, agent supervision, and even gaming…
Jev nedir? TypeSafe AI tarafından geliştirilen Jev neden bu kadar konuşuluyor? Bu videoda Jev AI modelini, GPT, Claude ve klasik LLM modellerinden farkını detaylı şekilde inceliyoruz. Jev, uzun uzun metin üreten klasik yapay zeka modelleri…
Agent evals and guardrails in one request. Built on Jev, Kev and Laya.
A Chinese-language overview of Jev and its use in AI workflows.
A Chinese guide to atomic questions, confidence routing and Jev API primitives.
A Japanese-language look at a development loop combining Codex and Jev.
A Czech-language overview of Jev and its decision-focused approach.
Explores how Jev can make AI agent decisions faster.
A shared demonstration of a Jev-driven decision loop in a driving simulator.
Chetaslua applies five yes/no questions to both candidates in a debate. The creator explicitly describes this as an experiment, not a fact-check.
A shared technical talk about Jev and decision-focused models, featuring TypeSafe founder Diogo Almeida.
An explanation of state inputs, questions and structured outputs, including yes/no, choice and score examples.
Avenox explains Jev in Turkish and tests classification, tool selection and its limitations.
Simone Rizzo explores structured decisions, automation and research into Jev-like models.
Rob Shocks demonstrates the playground and explains the decision types and potential developer uses.
Matthew Berman examines Jev and examples from its early developer community.
A discussion of email triage, lead scoring, browser control and business uses for Jev.
Heba Ahmed explains Jev in Arabic and demonstrates message classification and browser navigation.
A long-form stream exploring Jev and the idea of models built for structured decisions.
Prompt Engineering benchmarks Jev against older classification approaches and discusses instruction following.
AI随风 explains Jev’s output types and demonstrates resume screening.
dreadjordan discusses the claims around Jev and critiques the way early demonstrations are presented.
Panda Making Money examines Laya’s claims and the caveats behind comparisons with Jev.
Fazt introduces typed decisions, probabilities and the situations where Jev may fit an agent workflow.
TheAIGRID introduces Jev and discusses the attention around its decision-focused approach.
Melvynx examines demos, classification and real application experiments, including their limits.
AISeeKing explains decision primitives and separates structured outputs from guarantees of correctness.
Moritz introduces Jev and walks through how to use a decision model in applications.
Syntax explores what Jev does and demonstrates possible uses for structured decisions.
Julian Goldie presents a range of Jev application ideas and workflows.
윤자동 explains the basics of Jev for viewers new to decision models.
AICodeKing tries Jev in a browser-use workflow and discusses the experience.
Steve from critiques viral demos and discusses how to assess their claims.
Sam Witteveen examines Jev’s structured decisions and compares its role with other model approaches.
A hands-on introduction to the Jev model and experiments with its decision outputs.
AI mit Arnie discusses Jev and its approach to fast decisions inside software.
David Ondrej explores how to use Jev as a decision component in applications.
성공지식백과 introduces Jev and examines the claims around its decision-focused design.
코드깎는노인 discusses how Jev differs from familiar language-model workflows.
AI Revolution reports on Jev’s release, model design and early developer interest.
Riley Brown covers model routing, decision types and possible uses inside software.
Takafumi Horie discusses the model’s focus on decisions rather than text generation.
Jeremy Chone works with TypeSafe’s API and develops a Rust library in a live coding session.
Julian Goldie walks through an open-source browser agent that combines speech, Jev and Playwright.
01Coder tests the decision primitives and demonstrates routing, triage and content checks in a playground.
Carlos Alarcón explores the model’s decision types and tests practical classification scenarios.
Caleb Writes Code introduces TypeSafe’s model and discusses probabilities, speed and potential value.
usutaku explains Jev in Japanese and discusses early applications from developers.
Nate Herk tests classification and automation scenarios, including an X feed classifier and a paper-trading prototype.
A Korean-language short introducing Jev as a fast decision model.
A Korean-language analysis of Jev and its speed claims.
A one-hour course on building and automating with Jev.
A Spanish-language introduction to what Jev is and how to use it.
AICodeKing presents a coding setup that combines planning, decision making and worker models.
Meydeey examines Jev through automation experiments and discusses when to use a decision model.
JoCoding discusses Jev as part of a longer roundup of AI developments.
Matija Sosic gives a short explanation of the core idea behind Jev.
A French-language introduction to Jev in a broader discussion of ecommerce and AI agents.
A short setup guide for connecting TypeSafe's decision model to a Claude Code workflow.
Mike Codeur explores Jev’s primitives, tests intent routing, and discusses applications in his SaaS products.
An introduction to Jev's probabilistic outputs and how its decision role differs from text-generating LLMs.
A walkthrough of Jev's typed decisions and a linked collection of 50 creator-built examples comparing Jev with an LLM.
Examines whether Jev can reduce hallucinations in AI workflows.
Crush 好感监控器:用 Jev 分析微信聊天的情绪、意图和回复表现。本机部署,使用自己的 API Key。
TypeSafe founder Diogo Almeida introduces Jev, a model designed to return structured decisions rather than generated prose, and outlines the ideas behind its launch.
A recorded talk by Jev founder Diogo Almeida covers the model's decision-oriented design, RLCD training approach, and the team's view of where it fits alongside generative assistants.
Eugene Cheah introduces SimpleJev, an open-source library and API for adapting Hugging Face models to Jev-style structured decision tasks, including vision inputs.
Two-stage JEV control of a Franka Panda in MuJoCo.
Rank Pi Agent Skills for the current task with TypeSafe Jev
Video unavailable. Open the source below.
NewA Chrome-extension demonstration uses Jev for intent-based find on a page.
Video unavailable. Open the source below.
NewA custom-keyboard experiment uses active-application context to predict and highlight the next key, command or phrase.
Video unavailable. Open the source below.
NewA creator-posted Minecraft speedrun pairs Jev movement decisions with asynchronous Astra planning on a specified seed.
Astra planner and JEV controller for Minecraft, with native recording, tested routes, and run verification.
Jev DSH 决策引擎|面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness,通过 iPolloWork 支持 OpenCode、Codex Harness。
Video unavailable. Open the source below.
NewA creator demonstrates article and job searches with a Jev browser skill in Antigravity CLI and Codex.
EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs.
Video unavailable. Open the source below.
Newwhat if copy/paste was smart? powered by @typesafeai jev it feels like every computer interaction will get rewritten
Jev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.
Video unavailable. Open the source below.
Newjev KILLED the focus group. it scrolled 723 ads as 30 buyer personalities 21,690 stop or scroll decisions. 22 cents. (will be avail in @StealAds + mcp)
Video unavailable. Open the source below.
NewJev + GrokBot is the best AI agent system I’ve built in my life It just made my setup CHEAPER and FASTER than what 95% of people are running... setup takes literally 7 minutes: prompt → GrokBot → Jev decision → GrokBot execution → result s…
Semantic grep CLI where Jev judges which files and exact line ranges match a natural-language code query.
Video unavailable. Open the source below.
NewAn experimental terminal demo asks Jev to choose the next CPU-style instruction for a task at runtime.
1/ Jev, a decision model by @typesafeai, sparked a burst of projects and discussion. We tested it using Ori Eval against popular LLMs on OpenRouter at judging. Jev was >5x faster than the next fastest model, and even its slowest request…
Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev.
Video unavailable. Open the source below.
NewA Drape experiment uses Jev decisions to drive a virtual outfit-selection interface.
Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks.
Video unavailable. Open the source below.
NewJev killed 7 more SEO/GEO workflows 👇 1/ Assess which competitor pages to copy -> It scores every competitor page on answer, depth, proof and freshness, then checks its rank in Google and ChatGPT to show which ones are worth copying 2/ Ide…
Video unavailable. Open the source below.
NewAn open-source CLI helps developers tune Jev criteria using good and bad examples.
Open-source AI email triage for Gmail. Sorts your inbox into Needs reply, Updates, Promos, Sales and Spam with Jev, TypeSafe AI's decision model, via Vercel AI Gateway. Read-only, runs locally, 1,000 emails in about a minute for 3 cents.
Video unavailable. Open the source below.
NewUsing Jev to filter through my @wip todos It allows me to super quickly find all the instances where I increased revenue, got stuck, switched to a different SaaS provider, etc Things a regular keyword search would never catch
Video unavailable. Open the source below.
NewJev can serve as better natural language search on websites. It can scan thousands of Zillow listings and classify properties by things you can't normally filter for - e.g. architecture, renovation status, proximity to freeways. This was d…
Video unavailable. Open the source below.
Newtoday i'm releasing Jev for content marketing. still doomscrolling to figure out what to post on social media? that's over now... Jev watches EVERY video in your niche and judges it before it ever reaches you: 1. research: pulls every vide…
用 TypeSafe Jev 推荐已安装 Skill / Bounded installed-skill recommendations with TypeSafe Jev. Python CLI, Codex skill, bilingual docs and live examples.
Video unavailable. Open the source below.
NewJev is tagging X posts in real time for me. Breaking, golden nugget, or slop.
Video unavailable. Open the source below.
NewI just built a Jev X Viral Post Analyser. 100,000 viral X posts. 20.4 seconds. $0.67. Claude Opus 5, same corpus, same clock, got through 214 posts and spent $0.98. per post that is ~680x cheaper the full Opus pass would have run $458. vir…
Video unavailable. Open the source below.
NewWe turned Jev into a general browser skill for agents: jev-browser. Give it a website and a task. The browser opens automatically, and Jev decides every click based on what's on the screen. Here's a demo:
Video unavailable. Open the source below.
NewJev brought us closer to JARVIS it instantly does things like launch agents on a canvas - without awkawardly waiting for slowGPT LLM loop @clonkapp is now the fastest agent orchestrator on the planet
Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model
Video unavailable. Open the source below.
NewJEV IS INSANE. I gave it 80 real exam questions and 297 practice ones. In 80 seconds, it told me which ones are most likely to appear on the real exam and which ones aren’t. All for $0.0256. Can't stop playing with @typesafeai 😁
Video unavailable. Open the source below.
NewA creator reports using Jev in a client-site audit workflow; claimed savings and output quality have not been independently reproduced.
Video unavailable. Open the source below.
NewA creator-posted accounting prototype connects the Jev API to a mock interface.
Video unavailable. Open the source below.
NewJev classified 1,315 X posts for about $0.086 in estimated model cost 😂 seeing everyone's Jev demos made me want to build something for my own content research. i'd collected a lot of posts, but figuring out what they had in common still m…
Video unavailable. Open the source below.
NewJEV makes competitor research feel like a cheat code. Give it your competitors’ ads. Break them down by hook, angle, offer and format. Then turn recurring combinations into a shortlist for your next creative test. From an endless swipe fil…
Video unavailable. Open the source below.
Newyou can make any open source model behave like jev with just a bit of inference engineering. it's shockingly easy. to prove it, we built a new endpoint we're calling deepseek-v4.1-flash-jev. see the demo below. here's how it's done: sglang…
Video unavailable. Open the source below.
NewJev is INSANE. I asked 100 Indie Hackers to build a post scheduler with: Jev vs Fable 5.1. The results are unexpected 🤯 (You can clearly see Jev is faster at doing stuff)
Video unavailable. Open the source below.
NewA real-time calculator demo sends changing interface state to Jev and displays the returned decisions as immediate results.
TypeSafe Jev action selection inside Codex Computer Use
Grep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を、英語で日本語を検索できる.
Video unavailable. Open the source below.
NewJev is really good at content filtering and asset selection. DeepSeek + Higgsfield turn the selected assets into ad creatives.
Video unavailable. Open the source below.
NewJev is now live on the Venice API. Watch it classify 24,000 Hacker News posts into 12 categories in about 2 minutes
Video unavailable. Open the source below.
New型付き意思決定AIモデル「Jev」で双腕ロボを動かした結果まとめてみた🦾 3層制御のうち意思決定(2層)をJevに任せ、IKや物理計算はコード側に分離する構造を作りました。500msの応答と0.5円/試行で早くて激安。
Video unavailable. Open the source below.
NewJev dropped the price of SEO/GEO fixes by 90% Agents that audit and fix a client's SEO/GEO used to cost us ~$250 Here's where the savings come from: 1/ 30x faster reads of Search Console and PostHog/Mixpanel data 2/ 30x faster checks of wh…
Jev monitors more than 25 customer WhatsApp groups in real time and alerts an LLM when urgency, unresolved problems or orders require attention.
Video unavailable. Open the source below.
Newtoday i built talkr, a speech analyzer using @typesafeai > talkr gives you a topic > you talk about it for 30s > jev analyzes your speech: pauses, filler words, repetitions, confidence, clarity > you get a score and feedback to…
Video unavailable. Open the source below.
NewVideo unavailable. Open the source below.
New@typesafeai's Jev controls the 2 hands and each finger to play the piano in real-time. Jev only "sees" what we see and plays this from the "note waterfall". It uses @browser_use's jev-ultrafast and some decision scheduling to make this hap…
Talk to your Mac. Local + one Jev (TypeSafe) call per command + macOS automation.
Video unavailable. Open the source below.
NewI built a tool that finds App Store keywords by reading the competition, and uses Jev to judge them. What it actually does: 1. Turns the app's own listing into a handful of search queries, with Jev filtering out the ones nobody would type.…
Video unavailable. Open the source below.
NewWe built a plugin that gives Jev a browser in Cline, and have been blown away by the results. 1. Install it in our new desktop app: Customize > Marketplace > Plugins > search 'jev-browser' 2. Create a Vercel AI Gateway API key, then save i…
Video unavailable. Open the source below.
NewYou can use Jev to flag all the slop that Opus likes to write
A Jev toolkit for agent model routing, memory filtering, compaction, skill selection, triage, and bounded computer/browser decisions.
Video unavailable. Open the source below.
NewWOW 🤯 i just used Jev + @agnt_gg to categorize 63,045 emails in less than 3 minutes for < $1 total runtime: 2 minutes 54 seconds input tokens: 23,430,692 output tokens: 4,528,206 total tokens: 27,958,898 estimated cost: $0.9841 this wou…
Video unavailable. Open the source below.
Newbreaking: Agentcard + Jev + Kernel = Hipershopping ⚡ asking an agent to go buy stuff for you online is usually: - expensive (bc of tokens going back and forth) - slow (bc of tokens going back and forth) - unsafe (bc there's no safe/complia…
Video unavailable. Open the source below.
Newbest coding agent use case for Jev: enforcing rules a linter can't coding agents tend to break rules and some rules can't be codified Jev can now score every turn against such rules and tell the agent what to fix asap open-source:
Video unavailable. Open the source below.
NewToday I’m excited to show you our new harness called AgentRun, built with @pidotdev and @typesafeai's Jev. It’s built for an agent to learn how to do a job, code itself a general solution, and then get out of the way.
Video unavailable. Open the source below.
NewJev-thoven composed this entire 2 minute song from first principles.
Video unavailable. Open the source below.
NewI gave Jev the ability to draw pixel art! It uses deepseek to plan a sketch with some primitives, then renders it, refines it, all based on pixel positions and colors. Long way to go but it's pretty neat.
Video unavailable. Open the source below.
NewMade Jev fight OpenJev in a first person shooter.
A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.
Video unavailable. Open the source below.
NewCan Jev read a human? Play rock paper scissors against Byte. Every round he predicts your next throw before you make it, then plays against that read. His move is committed before you pick, so he can't change it after. Stakes settle over A…
Video unavailable. Open the source below.
NewPeople keep thinking Jev is useful for browser use! It is not. It completed about 5 actions before collapsing in a non-cheated test. It's a cool model but not for this.
Video unavailable. Open the source below.
NewJev beat Super Mario Bros. Every moment, the simulator returns structured data of the game's current state, such as Mario's position, nearby enemies, and terrain, and simulates possible actions like jumping and running. Jev returns a proba…
Video unavailable. Open the source below.
NewAn experiment combines json-render with Jev for responsive generated interfaces.
A local browser-grounded research agent lets Jev choose bounded operations across Instagram, TikTok, and LinkedIn.
Video unavailable. Open the source below.
NewJev is WILD for SEO audit 🤯 in 45.1 seconds it read all 586 pages on my site and rebuilt the internal link map. 584 links placed, 139 pages it refused to link because nothing honestly fit. total cost $0.21. Claude Opus 5, same 586 pages, s…
Video unavailable. Open the source below.
Newtested Jev as a real-time robotics policy in MuJoCo it struggled at first, so i split each update into two calls: decide what to do next, then decide how to move the arm and gripper Jev doesn’t accept images, it gets simplified geometry an…
Video unavailable. Open the source below.
NewAlso been playing with @typesafeai Jev. Insane. A pile of apps suddenly become possible. What a time to be a builder. Sharing experiments here. First one: Keystroke oracle / predictive launcher A normal launcher ranks by aliases, fuzzy mat…
Video unavailable. Open the source below.
Newit's f*cking insane Jev sat between GPT and me, killing every draft that broke my rules before i saw it. good setup. then Jev did not answer. the agent decided silence was safer and stopped sending me anything at all. took a second agent t…
Video unavailable. Open the source below.
NewJEV is INSANE. We gave it 3 million replay events In 40 seconds, it watched 3,247 sessions, caught 132 rage clicks, 116 dead clicks and 95 JavaScript errors, and opened 213 draft PRs to fix them. All for just $2.17. JEV can also flag aband…
Video unavailable. Open the source below.
NewJev vs GLM 5.3 at chess! Results: ◾ GLM 5.3 won by checkmate in 29 moves ◾ Jev: ~0.3s and <$0.0001 per move ◾ GLM 5.3: ~5.8s and ~$0.008 per move ◾ The whole game cost 24 cents My main takeaway is that it's often useful to use each one to…
Video unavailable. Open the source below.
NewA Box demonstration uses Jev decisions to organize incident reports into escalation, monitoring and review folders.
Video unavailable. Open the source below.
NewAlright playing with Jev through Vercel. 1. quick coaching support during a session rather than running through my gateway. 2. Anti-slop detector and fixer.
Video unavailable. Open the source below.
NewI used Jev to build a query planner! With some tuning, I sped up Postgres queries on the join order benchmark by 12%. Here's what I did
Video unavailable. Open the source below.
NewJev does in fact work for building @clay workflows instantly
Video unavailable. Open the source below.
Newthanks to @typesafeai jev I no longer have fill out all of those fields on prompt boxes. It picks the agent / model / computer / folder for me. - For a major rewrite it uses Fable + Claude Code. - Changes to an ios app run on one of my macs
Video unavailable. Open the source below.
New🆕@typesafeai dropped Jev this week, a new frontier model optimized for decisions. We put it to work on an incident triage workflow in Box. Jev doesn't generate text. You send it state plus typed questions and it returns booleans with proba…
A Codex computer-use skill that asks Jev to choose actions from accessible on-screen controls.
Video unavailable. Open the source below.
NewJev from @typesafeai plays @BalatroGame. Every hand it sees the cards, jokers, and blind, then picks play or discard in ~200–500ms. After the ante, it shops too. A full run costs less than a cent.
Video unavailable. Open the source below.
NewJev made our Slack agent 2x faster ⚡️ Our agent can be quite slow because it needs to read skills and figure out which tools to call. We used @typesafeai's new model to speed this up by first passing it the prompt and classifying the best…
Video unavailable. Open the source below.
NewPlayed around with @typesafeai Jev today, mostly to understand what it does for tool calling. Instead of an LLM deciding what to do, I substituted that part with Jev. My learning is that we will be able to make the agent act before the use…
Video unavailable. Open the source below.
NewIntroducing Jev Reviewer, a tool designed for systematic reviewers to quickly find and extract the information from research articles. App: GitHub:
Video unavailable. Open the source below.
NewJev can't reason. So I built an interpreter that reasons for it. It runs a logic language where the facts and rules are plain English.
Video unavailable. Open the source below.
NewTypeSafe's Jev plays Tetris better than me!! We hooked it up to a Tetris game. Every piece, it looks at the board and all the spots the piece could land, and picks one in about half a second. A whole game cost us less than half a cent. The…
Video unavailable. Open the source below.
NewJEV is Awsome!!! 😎 360 resumes Screened in 24.2s — $0.0212. Typed scores. Shortlist signals. Speed + cost your boss will quietly love. I Open-sourced the resume screener on YouWare. Reply “JEV” to try it. We’re bringing JEV to YouWare soon…
Video unavailable. Open the source below.
New@typesafeai Jev is FREAKING SICK!! Playing around with it to create an experimental RLS Linter for @supabase. You can check it out here: or view the demo 📺
Video unavailable. Open the source below.
NewJEV is INSANE. We gave it 400 companies and one candidate profile. In 12 seconds, it predicted which jobs the candidate had the highest chance of getting, assigned a confidence score and detected job-candidate mismatches. All for just $0.0…
Video unavailable. Open the source below.
NewDoc-OCR router using Jev @typesafeai A Jev-powered router that looks at a PDF page by page, decides which pages actually need OCR, extracts the rest locally. Result: save cost on # OCR pages + speed
Video unavailable. Open the source below.
NewMade a real-time slop detector with jev as you scroll
Video unavailable. Open the source below.
NewJev lets me search my physical library by looking at the entire book index in parallel in 300ms. Here, the answer to “Who invented photography?” is probably on page 98 under "Niépce, Joseph Nicéphore"
Video unavailable. Open the source below.
NewA creator demonstrates a Jev tax-document classifier. Reported accuracy, speed and costs apply to the creator’s corpus and are not independently validated.
Video unavailable. Open the source below.
NewVideo unavailable. Open the source below.
NewHad some fun taking Jev from @typesafeai for a spin, switching seamlessly between manual and AI-driven gameplay. It’s clocking 2–3 calls/sec at 60 FPS, with ~150ms avg latency. The most interesting part wasn’t the speed, though. It was dis…
Video unavailable. Open the source below.
Newego lite + Jev + DeepSeek Flash = stupid fast. ⚡ 3.71s for 20 Amazon product decisions. GPT-5.6 Sol: 54.45s Same task. Same result. 10/10 on both. Less reasoning. Faster decisions. 1× speed.
Video unavailable. Open the source below.
NewI wanted an easier way to test my jev requests and see if my results are improving, so I built jevals! It's a local workbench for testng the Noul, Choice, and Score primitives. You can mix requests as well. You can run a seed command to se…
Video unavailable. Open the source below.
NewAi is evolving. Jev can be armed at all times. I can speak freely and it knows ( from probabilities ) if im asking my computer to do something or blaberring away at something else. no wake word. speed + affordability + intelligence is gett…
Video unavailable. Open the source below.
NewWe put Jev inside OmarchyLinux @dhh to play Connect Four. It reads the board, chooses a move, watches the opponent respond, then Hermes reviews the result and tries again. 6,499 model tokens. Cost: $0.00022113. This is what structured stat…
Video unavailable. Open the source below.
Newe2e + jev from @typesafeai ⚡ I'm building an open-source framework for running e2e tests with agents. supports web, mobile (and more!) available soon:
Video unavailable. Open the source below.
NewGM Jev V1 is live on Here's what's new: TRADE • Paste any Solana CA and get a live chart with Jev watching it with you • Jev re-reads the token every 5 seconds: the call, where price is in 15 minutes, buyers in control, dump risk, alive in…
Video unavailable. Open the source below.
NewCorent’s brain uses @typesafeai Jev now. Not to generate the output, to make the decision before the output gets generated. When a request comes into Corent, you don’t need to tell us which model to use. You send the prompt, the workload a…
Video unavailable. Open the source below.
NewJEVINIK - Evaluating stocks insanely fast with @typesafeai's Jev It pulls market data, signals, risk & filings around any stock, then calls the next 30 days: 🐂 BULLISH 🐻 BEARISH No LLMs. No vibes. Just Jev & @ValyuOfficial rich financial d…
Video unavailable. Open the source below.
NewJev playing the piano. I gave it the key, all 88 notes to choose from and the sequence so far. Did chords in a second pass once we had the melody by giving it the bar's notes & 7 chords to choose from. Plays it safe & loves alternating bet…
Video unavailable. Open the source below.
NewJev is so cool! I just made Jev conduct a musical orchestra in REAL time My entire TL was filled with Jev demos so decided to give it a spin and needless to say, I was not dissapointed.
Video unavailable. Open the source below.
NewYes yes, Jev can drive, Jev can be a programming language... but lets just skip the middle man ... Jev be the "computer" !!! Motorola 6502 emulation directly on Jev 🤣😅 @typesafeai @dotpem Took a bit "hill-climbing to figure out how to inst…
Video unavailable. Open the source below.
NewUsed Jev to build voice builder in Youform. It is so fast!
Video unavailable. Open the source below.
NewVideo unavailable. Open the source below.
NewJev is crazy 🤯 I made an AI text detector powered by Jev. Scans a complete article and gives a sentence by sentence breakdown in almost realtime.
Video unavailable. Open the source below.
Newlet Jev automatically transmogrify your simpleton English into unnecessarily fancy prose as you're writing it 😅
Video unavailable. Open the source below.
NewMade myself a little image classifier with OCR + Jev It was able to categorise ~900 images in 40 seconds Pretty cool
Video unavailable. Open the source below.
NewJev can generate game levels in real time. Faster and cheaper structured output could be a big deal for game dev!
Video unavailable. Open the source below.
NewVideo unavailable. Open the source below.
NewJev is INSANE. 🤯 in 24.9 seconds it read 384 news from this morning and told 15 brands which stories to hop onto today, for $0.19. Claude Opus 5, running on the same feed at the same time, got through 4/384 and cost $0.77. per headline tha…
Video unavailable. Open the source below.
NewJev flying a drone through an asteroid field. 300ms decisions. Left / right / slow / accelerate. You can watch the decisions happening live on the right. Green = Jev’s own confidence. Purple = “I’m not sure, ask the big model.” 99% of the…
Video unavailable. Open the source below.
NewESTA HERRAMIENTA ACABA DE ROMPER TODO EL MERCADO DEL AD SPY Maxfusion ha cogido JEV, el modelo nuevo de TypeSafe, y le ha metido la ad library entera de una marca → 1.891 anuncios clasificados → 19 segundos → 0,12 $ Y no es un resumen: cad…
Video unavailable. Open the source below.
Newjev is an insanely cool product Saw a post about jev and decided to check it out This thing is straight up gold whoever built it is a genius jev is the future Scanned over 700 live ads in 40seconds flat, and it cost me just 4 cents. If you…
Video unavailable. Open the source below.
NewI'm laughing out loud. I turned Jev into an improv judge. Introducing: 'Whose Jev is it Anyway?'
Video unavailable. Open the source below.
New🚨Do not record Jev demos while @ogme01 flies a drone over your desk 🚁 You can now dictate attaches, updates, schedules & more in the @autumnpricing dashboard, no more manual edits Safe to say my tenzing tower didn't survive this one th…
Video unavailable. Open the source below.
NewJido Jev + ReqLLM playing Tic Tac Toe Each agent makes Jev calls to determine their next move, pretty fun! Now time to scale up ...
Video unavailable. Open the source below.
Newgave jev a way to express some emotion and chat with beeps (sound on 🔊)
Video unavailable. Open the source below.
NewJEV makes competitor research feel like a cheat code We fed it Resilia’s ad library and it classified 1,891 ads in 19 seconds for $0.12 Customer journey stage, ad style, and a full account deep dive Coming soon to the maxfusion MCP
Video unavailable. Open the source below.
NewJev trading the danish stock market for all of 2025(239 trading days). Sentiment-based on market data, news articles, wikipedia & google trends. 8.1 million tokens for $0.32 🤯
Video unavailable. Open the source below.
NewJEV is insane for competitor research! We gave it Resilia's ad library It classified 1,891 ads in 19 seconds for $0.12 costumer journey step + Ad style And a complete deep analysis of the account Coming soon to maxfusion MCP
Video unavailable. Open the source below.
Newgave jev a pixel canvas to see if it could draw... nope
Video unavailable. Open the source below.
NewLet Jev roast your fighting habits 👇
An open benchmark pairs Jev tool selection with Mercury-generated arguments.
Video unavailable. Open the source below.
NewStarchild just became the first professional-grade app to integrate Jev from @typesafeai We use Jev to help route to LLMs which gave a 20x decrease in cost and 6x increase in speed for prompt classification Here it is classifying prompts i…
Video unavailable. Open the source below.
NewThat’s Jev playing Floppy Apex, passing the previous best score and not thinking of stopping anytime soon 🏆 It was wired up by Apex via Appduct, with some adjustments made in Fable. @AgentConf
A Rust CLI and MCP server uses Jev to route and score zero-cost SEO and generative-search research tasks.
Video unavailable. Open the source below.
NewI rebuilt my job crawler with Jev. The task: start at a company's official homepage, find Careers, and identify jobs that match my profile. Before, with an LLM: ~5 minutes. After, with Jev: just over 20 seconds in my test. Every company or…
Video unavailable. Open the source below.
NewExperimentation with Jev from @typesafeai and our harness @goose_oss Use Jev to take a prompt and JIT select a model just before the turn runs. Jev and models like it will be useful in many areas and this is just early prototype code on a…
building a computer assistant with Jev local whisper listens to everything I say which then gets classified by Jev to determine what actions to take it uses a small Swift app to provide the full accessibility tree to Jev (i.e. tell its wha…
Video unavailable. Open the source below.
NewGot early access to @typesafeai Jev and spent a few hours building on it. The problem I keep hitting: agent traces tell you which tool ran, how long it took, what it returned but never whether the agent is actually getting anywhere. An age…
Video unavailable. Open the source below.
NewI love that Jev can fit into basically any app. You don't need to build everything around a chat, you can just integrate intelligent features into the background, like these auto-fill buttons. Much better UX than with slow LLMs. Feels like…
Video unavailable. Open the source below.
NewAdaptive real-time in-app support with Jev + It detects where you're struggling and quietly adds help directly into the UI - explanations, suggestions, even actions. Jev figures out if and where you're struggling, then triggers the right f…
Video unavailable. Open the source below.
NewShipper presents a Jev-assisted workflow for turning website URLs into mobile applications; the full build path is not independently reproduced.
Scans a codebase for covert, deceptive, or data-stealing behavior with Jev, then reports suspicious files and line ranges before the user runs it.
Video unavailable. Open the source below.
NewJEV is insanely fast. We gave it a massive dataset based on thousands of outreach messages and asked: Which intent signals generated the most booked demos? 40 seconds later, we had the answer. Cost: less than $0.20. JEV can also rank leads…
Video unavailable. Open the source below.
NewA search bar that knows when it doesn't know. cascade-search is a 27K-parameter model that parses queries like "open bugs from sam since last week" into typed filters, in your browser, in 0.25 ms. When it isn't sure about a word, it asks J…
Video unavailable. Open the source below.
NewJev also constantly monitors my macOS clipboard. Is the content of the clipboard a terminal command? The app offers a quick action to run it in my terminal.
Video unavailable. Open the source below.
NewA macOS demo organizes downloads according to natural-language rules.
Video unavailable. Open the source below.
NewJev + API = find best overlap among team members in an instant the longest waiting time is our API call round trips 🤯 will come up with ideas how we can bake Jev into our products
Video unavailable. Open the source below.
Newdoes Jev understand colour? incredible model, very cheap and fast. definitely feels like a leap forward for creating new UX/UI paradigms on top of modern language models.
Video unavailable. Open the source below.
NewWe built "Worth Replying" with Jev + AIsa. Drop in a company’s domain and it finds people on X already talking about the problems your product solves. We tested it on > 150 tweets found > 750 Jev decisions in 18.8s > 79 worth replying to >…
Video unavailable. Open the source below.
NewJEV is INSANE. We gave it 700 high-intent leads and personalised outreach messages. In 40 seconds, it predicted how each message would perform, assigned a confidence score and detected lead-message mismatches. All for just $0.09. JEV can a…
Video unavailable. Open the source below.
NewPro tip: You can use Jev to remove annoying reply guy comments that X seems to always miss. Takes 5 minutes in Astra with the docs and an API key.
Cloudflare Workers has Jev now so I'm putting it to the test on - 7x faster search rerank compared to the current hybrid - 50x faster tagging of content vs GLM 4.7 Flash with no failures
Video unavailable. Open the source below.
NewMade Jev play Clash Royale and actually won a match.
Video unavailable. Open the source below.
Newthanks to @typesafeai's Jev we now have massively parallel browser-based adversarial testing suite that tries to break each release. and it costs pennies.
Video unavailable. Open the source below.
NewOrganically integrated JEV in a real project The Paper Breakdown Recommendation Engine We already had a working system that combines content-based and collaborative filtering. Pro users may now get additional curation with Jev. 0.0019$/use…
Video unavailable. Open the source below.
NewA town simulation with residents, businesses, public decisions and disasters.
Jev picks which of your rules apply to each prompt, so Claude only sees the ones that matter.
A lightweight Jev-powered router for models, tools, and subagents.
Video unavailable. Open the source below.
Newi made a smart calculator notebook using jev it can calculate ANYTHING!! 😅
Video unavailable. Open the source below.
NewJev is insane for ad research. I built a tool that scores every shot of any video ad on meta in 1.5 seconds. It runs on Maxfusion + @typesafeai I pushed 450+ ads through it in less than 3 minutes. It pulls any advertisers live video ads fr…
Video unavailable. Open the source below.
NewA creator compares a Jev-assisted calendar workflow with Codex computer use; the claimed speedup has not been independently measured.
A command-line toolkit exposes Jev verification, classification, extraction, ranking, routing, compaction, and custom typed decisions for scripts, CI, and agent workflows.
Fish-style zsh history autosuggestions ranked by Jev (TypeSafe).
Video unavailable. Open the source below.
NewAs promised, Jev is now integrated into Orus agents. What is Jev, and how can it help our agents? Jev is a model from TypeSafe AI, built to answer precise questions with structured answers. In Orus, it reviews the trades your strategy prop…
Video unavailable. Open the source below.
NewJev picking the next command from shell history
Video unavailable. Open the source below.
Newi made a calorie tracking app with jev. it's INSTANT 🤯
Route HTTP requests by meaning. A semantic router for Hono powered by Jev.
Video unavailable. Open the source below.
NewI gave Jev a robot arm. Two USB cameras, an SO-101, and @typesafeai's Jev choosing the next move at ~2 decisions a second. After a slip and some debugging, it went back for the ball and got it into the bowl.
Video unavailable. Open the source below.
NewEveryone picks Jev confidence thresholds by vibes. 0.95? 0.5? I built jevcal. Give it your data and say "I need 99% accuracy". You get the exact threshold, how much Jev can handle, and how much still needs an LLM. Open source, one command.…
Video unavailable. Open the source below.
NewControlling Figma with voice using Jev from @typesafeai Total cost from first line of code to recording this video: $0.01 🤯
Video unavailable. Open the source below.
NewJev by @typesafeai is amazing! i let it play pokemon firered, and it was able to beat elite 4 with a party of level 40 pokemons. all under 0.03$
5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.
Video unavailable. Open the source below.
Newi wanted to paint with Jev 🎨 watch this beautiful painting of the Golden Gate Bridge, powered by Codex(Astra) + Jev + @Stagehanddev + @browserbase (video at 1x speed)
Video unavailable. Open the source below.
NewJust hacked a fun little project - Skill Router (Open source) using Claude and Jev @typesafeai Why? I have ~ 90 Claude Code skills installed and use maybe five. The rest are fine, I just forgot they existed, and Claude won't reach for a sk…
Video unavailable. Open the source below.
NewGot @typesafeai Jev driving our @makermodsai Metal arm in MuJoCo. Images are of the sim camera is not passed in, sim hands Jev the state of the environment in JSON and it picks the next bounded action (hover, descend, grasp, lift, place) a…
Video unavailable. Open the source below.
Newi added Jev compaction to a small agent with searchable memory. this is a fork of nanocode with some extra tools to grep a file + use Jev compaction to remove unnecessary memories.
Video unavailable. Open the source below.
NewJev demo: A live Bluesky feed with real-time emotion detection and avatars matched to each user’s profile. #jev
Video unavailable. Open the source below.
New@typesafeai jev playing chrome dino! the model is incredibly fast! - avg response time: ~280ms - spent 116M tokens - cost? just $4.65. - the input here is a snapshot of the chrome runner - jev decides whether to jump, run or duck with a co…
Video unavailable. Open the source below.
NewI built a voice controlled computer-use for my mac using @typesafeai's Jev and it's INSANE how fast it is! I can dictate "open the notes app and create..." and the app opens before I even finish my sentence.
Video unavailable. Open the source below.
Newmy mobile e2e testing library powered by @agent_device and AI sdk now supports Jev from @typesafeai Same test, same loop: Jev: 29s, $0.003 Haiku 4.5: 37s, $0.07
Video unavailable. Open the source below.
NewJev is insane. We are building egocentric training data for physical AI. Jev QA'd 58,643 action labels in under 3 minutes. 90 cents. A friction cost of the Claude & GPT models.
Video unavailable. Open the source below.
Newsmall experiment where I used jev to power the global search in replicas. the possibilities of improving UX with models like jev are endless. we can now have things like: - search that understands what users mean - actions that change base…
Video unavailable. Open the source below.
NewFirst Jev use case published live on Bannerbear! Instant field mapping between template and source, when names are slightly different eg template - photo - name - company_name data source (eg Airtable) - avatar - full_name - business Jev f…
Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it.
ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
Video unavailable. Open the source below.
NewClaude me integró Jev con Playwright para buscar usados. Lee unos 26 artículos por minuto y decide qué hacer con cada uno en 406 milisegundos Descartó los que no encajaban con lo que busco, ofertó por los que sí y hasta les mandó un mensaj…
Video unavailable. Open the source below.
NewAlso have been playing with @typesafeai Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ran…
Video unavailable. Open the source below.
NewA Japanese-language demo sorts live comments into useful groups.
Classify first. Read selectively. A portable agent plugin and MCP tool for batch text classification.
Video unavailable. Open the source below.
NewA creator-posted gameplay demo presents Jev controlling four Smash characters; the underlying harness is not independently verified.
Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into
Detect youtube sponsor segment with live audio and transcript powered by Jev
Video unavailable. Open the source below.
NewA camera-driven canvas demo uses hand gestures as input and shows Jev choosing the next drawing action.
A Minecraft agent pairs Jev reactions with GPT-6 Astra planning.
Video unavailable. Open the source below.
NewJev + SuperX = virality solved ✅ Every post gets 61 questions in ~1s for $0.0004 🤯 > fitted on 9,481 real posts from 207 creators > picks the viral post 2 in 3 times > never rewards reply bait So: write, score, rewrite, stop when…
Video unavailable. Open the source below.
NewI built a visual reference finder with Jev One single prompt → 100 images from Cosmos, NASA, and The Met my new rabbit hole for creative work 🌻
Video unavailable. Open the source below.
NewA presentation demo changes slides as its presenter speaks.
A prose linter that combines local countable rules with Jev-powered judgment rules for writing checks.
Video unavailable. Open the source below.
NewJev is fun! One-click invoice finder for any website 🧾 - Automatically finds billing pages using @typesafeai's Jev - List/download all invoices with 1 click - Works with Stripe billing portals too - Remembers where invoices live for next t…
Video unavailable. Open the source below.
NewAn OpenCode plugin demonstration uses Jev to assess the intent of commands against an allowed-domain policy.
Video unavailable. Open the source below.
NewI built real-time Clippy with Jev. It quietly watches how you use the product and only wakes up when it thinks you’re struggling. Hesitating? Confused? Stuck? Clippy knows. Even its reactions are controlled by Jev. 👀
Video unavailable. Open the source below.
NewVideo unavailable. Open the source below.
NewA Claude Code plugin experiments with pruning context instead of summarizing it.
Caso de uso de @typesafeai: Revisar todas las facturas de la empresa y clasificarlas contablemente en segundos 🫠
A decision layer for agent ranking, verification and action assessment.
Filter, rank and classify PostgreSQL rows using natural-language conditions.
"Work appears completed or recorded. Run /compact to save tokens."
Video unavailable. Open the source below.
NewA continuous livestream lets Jev attempt to defeat Minecraft's Ender Dragon one decision at a time.
Video unavailable. Open the source below.
NewI gave Jev 3,282 of my X posts across 100M views and asked it to find what actually works for growth. 4,252,330 tokens $0.1282 for the full 8m 34s run! Each post got 8 questions about the topic, hook, tone, whether it teaches something, et…
Browser use using Typesafe's Jev model.
Video unavailable. Open the source below.
NewA demo assistant connects search, reference, weather and personal tools.
Trading bot with the all new TypeSafe AI's first system one model named as Jev.
Video unavailable. Open the source below.
NewAn experiment reconstructs a piano sequence by repeatedly choosing keys.
Video unavailable. Open the source below.
NewA creator demonstration applies Jev to a collection of live ads for structured marketing analysis.
Video unavailable. Open the source below.
Newi made a @typesafeai jev+chatgpt instance race against a purely chatgpt instance on two super simple tasks to see the difference, 2-3x faster! :o on first-time tasks chatgpt will write a question set for jev on the fly, and then subsequent…
A web-search application uses Jev to choose sources, time ranges and search terms, then rank returned links and snippets.
A Chrome extension lets agents browse and act in the current page with Jev decisions.
🧹 Fun project: a Chrome extension that asks a tiny AI decision model (TypeSafe Jev) "is this DOM element an ad?" and pops it off the page. BYOK, no backend, not a real ad blocker.
Self-hosted, versioned skills library for AI agents. MCP, scoped clients, and optional Jev recommendations.
Interactive TypeScript coding CLI with typed routing, decision programs, and validated formal trees driven by Jev.
Video unavailable. Open the source below.
Newjev is insane 🤯 Here is Jev playing subway surfers at super human speed, and also playing 50 games at once. cost less than a cent to do this run. Jev does not replace llms like astra or fable, but opens up an entirely new world of capabili…
I spent the last 8 hours building a viral post classifier with Jev. It's now better at spotting viral posts than I am. And it's as good as Fable 5.1, but 100x faster.
Video unavailable. Open the source below.
NewA Mac pointer experiment uses local OmniParser/CoreML detection and sends text labels to Jev to choose the next click.
Video unavailable. Open the source below.
NewAnnouncing Jev Detector The world's fastest AI slop detector, built on jev from @typesafeai ~10,000 words scanned for slop in ~2 seconds Best part, its free, no sign up required, enjoy!
Video unavailable. Open the source below.
NewJev just beat Brock in Pokémon FireRed in less than 5 minutes. That’s 5 minutes of actual real-world time. You can see the in-game time in the video. This is a completely different way of having an LLM play a game. Jev doesn’t see pixels o…
Video unavailable. Open the source below.
NewA remote-browser loop combines Jev action decisions with Stagehand execution.
Video unavailable. Open the source below.
NewA gameplay prototype uses Jev to automate Minecraft for extended sessions at low token cost.
Video unavailable. Open the source below.
NewA local web app classifies exported Telegram posts and conversations by intent, quality, sentiment, topic, and tone.
Video unavailable. Open the source below.
NewA CLI recommends an agent or model from a task and the user's available AI subscriptions.
Video unavailable. Open the source below.
NewA demonstration classifies a 100-email test set with Jev, then asks a larger model to handle uncertain results.
A driving simulator with inspectable AI autopilot.
A classifier produces small pixel-art images through repeated color choices.
Video unavailable. Open the source below.
NewA voice prototype uses Jev to decide whether a speaker has finished and how long to keep listening.
Video unavailable. Open the source below.
NewBuilding an agent with model router powered by Jev.
A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.
A PostgreSQL extension exposes Jev categorical classification inside SQL.
An evaluation harness comparing Jev with LLM judges on the same recorded agent runs.
Video unavailable. Open the source below.
NewA PR-review demonstration turns Jev probabilities into review routes, with uncertain critical checks handed to a human or larger model.
Video unavailable. Open the source below.
NewA voice-browser demo combines speech input and Jev-selected actions in a rapid interaction loop.
Video unavailable. Open the source below.
New昨天出的 Jev 模型 适合高频决策,那岂不又是适合打游戏? 之前用 GPT-6 Astra 代打杀戮尖塔2 能力强但速度慢。 我刚实测用 Jev 打,行动思考只需 0.7秒, 画面我都没看清它就操作完了。 这超人类游戏速度, 着实又让我震惊瘫坐了😅 语言很难描述这感觉,看视频⬇️
Video unavailable. Open the source below.
NewA creator tests Jev in a memory workflow and reports lower token use and faster retrieval; the measurements remain creator-reported.
Skillbox uses Jev to return relevant agent skills directly from a query.
A browser extension removes ads, cookie banners and other page clutter with reusable Jev rules.
An experimental supervisor uses Jev to assess and steer a coding agent.
A video tool scores each spoken sentence and renders an annotated 16:9 edit.
A web app asks Jev a set of parallel questions to decide whether a startup idea should be killed, fixed, or shipped.
Turn questions about household state into sensors and automation inputs.
Video unavailable. Open the source below.
NewAn Android agent navigates apps with a live studio and execution trace.
Video unavailable. Open the source below.
NewA creator-posted trading experiment shows Jev making decisions against a $10,000 account while a dashboard tracks the market, account and model output.
An AI-controlled Snake game with decision telemetry.
Video unavailable. Open the source below.
NewA browser extension hides posts that match a user’s natural-language rules.
Video unavailable. Open the source below.
Newgot @typesafeai's new model Jev as a chief of staff for bots Jev reads the task, wakes the right teammates off the bench and gives each one the right model It is possible on OpenMausBot as it supports all the LLMs from your existing subscr…
A music playground that turns a chosen style into sheet music, playback and MIDI.
Video unavailable. Open the source below.
NewYou can hire Jev from @typesafeai as your QA tester
An experiment that makes a non-generative decision model assemble a chat reply one word at a time.
A command-line tool classifies Git commits by change type, bug fixes and security relevance.
Video unavailable. Open the source below.
NewA cube-solving experiment lets Jev choose cases while deterministic code checks each move.
Now using @typesafeai Jev in etc AI ends up vibe coding so much AI regex slop if you don't read the code, so I can finally move all this hard-coding to Jev and it's insanely fast! Also for regular LLM calls, it is around 10x faster, 50% ch…
Video unavailable. Open the source below.
NewA stealth game where guards make inspectable judgments.
Video unavailable. Open the source below.
NewAn experimental market-analysis demo combines price forecasts with Jev decisions.
A Rust CLI ranks installed agent skills against live session context with Jev, then applies abstention and local feedback around the typed result.
Video unavailable. Open the source below.
NewA prototype uses Jev to simulate responses from fictional product personas. These are model outputs, not customer research.
Video unavailable. Open the source below.
Newrebuilt the X algorithm with Jev - uses real weights - simulates virality of your post - has a global feed (you see everyone) it's insanely accurate
A Discord bot uses Jev to filter spam and scam links and escalate repeat offenses.
Video unavailable. Open the source below.
NewJev is actually insane. We benchmarked it, and the results completely change the game for us: > 500 real-time agents > running in parallel > in a 3D environment The preliminary results are crazy: > 500ms average latency > 35 API calls/s >…
Video unavailable. Open the source below.
NewAn MCP tool supplies repeated software-quality measurements to coding agents.
Video unavailable. Open the source below.
NewA router uses Jev to choose the model that best fits each incoming request.
Video unavailable. Open the source below.
NewDuring a live clinical consultation (with an ambient scribe), the transcript is periodically supplied to Jev, which traverses a medical ontology to classify symptoms, update the differential diagnosis, suggest treatments and identify red f…
A personal-assistant agent uses Jev to select one tool from a 100-tool catalog before each model step.
A simulated RISC-V CPU uses Boolean lookup tables supplied by Jev.
Video unavailable. Open the source below.
NewPuse a Jev, la nueva IA de @typesafeai, a jugar al Tetris en modo súper difícil. Decidió cada jugada en unos 0,3 segundos. Acomodó 357 piezas e hizo 134 líneas en solo 2 minutos. Increíble.
these are results of using jev on one of our security pipelines. we already have to use smaller (and dumber) models to make it economic and this model does it over 5x cheaper, faster and while maintaining much higher accuracy. i don't norm…
Natural-language requests select and configure real UI components.
Ultra-fast, criteria-based model routing using Jev from @typesafeai.
Video unavailable. Open the source below.
NewAn experimental writing interface uses Jev to analyze posts while they are being drafted; predictive quality is unverified.
Video unavailable. Open the source below.
NewA browser agent selects actions from the current DOM and demonstrates flight search.
Video unavailable. Open the source below.
NewAcabo de terminar la implementación de @typesafeai + Chromium Headless para que mis agentes puedan navegar por internet a una buena velocidad! En este ejemplo le pido al agente que entre a la página del término "Café" en Wikipedia y navegu…
Video unavailable. Open the source below.
NewAn experiment builds text-like output by asking Jev to choose from a few hundred words and punctuation marks.
Video unavailable. Open the source below.
NewYeah Jev by @typesafeai is very cool. It classified 500 emails in seconds. And it costed 3.5 cents.
Video unavailable. Open the source below.
NewJev VS Fable 5.1 VS GPT-6 Astra: chess typesafe's new Jev V13 isn't an LLM. it doesn't chat, doesn't explain, doesn't write code — it only makes decisions. so we made it play blitz against frontier LLMs. the test: 5+0 blitz. every move is…
A DuckDB extension classifies rows in CSV, Parquet, and DuckDB tables with Jev.
Video unavailable. Open the source below.
NewA trading experiment connects rapid decisions to an on-chain order book.
A Minecraft bot gathers materials and builds a supplied Canadian flag blueprint.
Video unavailable. Open the source below.
NewI rebuilt Tesla Full Self Driving with Jev in less than an hour. This model is a total unlock.
A staged code-review workflow follows Jev signals through focused checks and a local dashboard.
Video unavailable. Open the source below.
NewA ViZDoom test uses separate Jev decision channels for navigation and combat.
A simulated drone navigates obstacles and reacquires a target.
A local router chooses a model tier for each Claude Code or Codex turn.
Video unavailable. Open the source below.
NewAn early-access gameplay demo shows Jev playing Tetris.
A browser-use preview pairs Jev decisions with OpenCode's browser-use CLI for fast interaction loops.
Video unavailable. Open the source below.
NewAn interactive browser demo lets people try Jev decisions directly.
Video unavailable. Open the source below.
NewA small app-testing demo uses Jev with OpenCode for a fast browser interaction loop.
Video unavailable. Open the source below.
NewI was wondering if @typesafeai Jev could generate images so here's what a sunflower looks like according to Jev :
A macOS computer-use loop uses OCR and Jev to choose bounded actions.
A codebase-search tool uses ensembles of Jev-guided filesystem walkers.
Video unavailable. Open the source below.
Newi made an llm from first principles with Jev 29 yes/no questions per character: should the next key be a–z, space, comma, or period? highest probability gets append to it, then fed the updated text back in & repeat an autoregressive lo…
A Pi extension gates tool calls, judges command output and exposes typed Jev questions.
Video unavailable. Open the source below.
NewJev chooses controller inputs for Super Mario Bros.
A Pi extension watches tool calls and agent progress for safety and completion problems.
Video unavailable. Open the source below.
NewA prototype uses Jev as a codebase classifier; the creator frames it as an experiment in reducing overengineering.
A Claude Code hook that filters large tool results before they enter the agent's context.
Pi extension with a Jev evaluation tool, terminal playground, and typed API for other extensions.
“Jev can’t generate text” Ofc it can @CompleteSkeptic
Explore graph paths with a visual Neo4j navigation demo.
The Loki agent offers Jev as an optional typed-decision companion and session model router.
Code quality and test coverage for coding agents: Jev scores each source file so the agent knows what to fix first.
An agent memory plugin that can ask Jev whether a new request needs a memory search.
duet-agent uses a Jev-backed routing table to select models for agent work.
A local memory system for AI agents with an optional Jev reranker for recalled notes.
A repository governance kernel can attach optional Jev trajectory observations to its assurance loop while retaining deterministic policy, interlocks and proof rules.
An interactive terminal extension that can use Jev to select useful output from captured command logs.
OpenWork uses Jev as a typed verification judge for agent-produced work in its evaluation testkit.
Smithers uses Jev checks and scores across repository and workflow automation.
An open-source quantitative research platform that documents Jev-powered pre-trade decisions alongside market data, backtesting and execution tools.
A Chrome control CLI with an optional Jev-driven semantic action loop.
A terminal tool exposes typed Boolean, Choice and Score evaluations with Jev as the default evaluation model.
NeuroLink exposes typed Jev decisions for routing, compaction, tool use, and retrieval planning.
A terminal coding agent uses Jev for typed turn, risk and progress judgments before its generative planning and tool loop.
Formanator can use Jev to select benefit and reimbursement categories for claims.
No content matches these filters.