An experiment using Claude Code with the Ralph technique to build a browser-based SQLite UI

Go from writing pipeline code to ingesting data and delivering reports via Notebooks - all in one flow. Discover over 10,100 REST API data sources today.

The dltHub Workspace is a dedicated environment for developers to create, debug, and maintain dlt pipelines. As the first workflow, we’ve launched LLM-native pipeline development for over 10,100 REST API data sources in the Workspace.

In this workflow you can generate the LLMs context for your source, can go from writing pipeline code to ingesting data and delivering reports via Notebooks - all in one flow, with outputs tailored to data users.

Tally is an open-source tool that works with AI assistants like Claude, Copilot, and Codex to automatically categorize your bank transactions. No cloud, no database - just a local file you control.

Production-ready platform for agentic workflow development. - langgenius/dify

Easy Data Preparation with latest LLMs-based Operators and Pipelines. - OpenDCAI/DataFlow

Analyzing Hacker News discussions from a decade ago in hindsight with LLMs - karpathy/hn-time-capsule

A Hacker News time capsule project that pulls the HN frontpage from exactly 10 years ago, analyzes articles and discussions using an LLM to evaluate prescience with the benefit of hindsight, and generates an HTML report.

A Model Context Protocol (MCP) server that facilitates structured, progressive thinking through defined stages. This tool helps break down complex problems into sequential thoughts, track the progression of your thinking process, and generate summaries.

Using LLMs to identify extraordinary prescience, confident delusions, and the madness of earnings calls. Inspired by Andrej Karpathy

Auto-Grading Ten Years of Earnings Calls for Prescience and Delusion

Earnings Call Civilizational Score Prompt. GitHub Gist: instantly share code, notes, and snippets.

You are a financial historian and industry expert conducting a review of past earnings calls with the benefit of hindsight and wisdom.

AI writing agent powered by gemini 3 flash - autonomously creates novels and stories with deep reasoning

An autonomous agent powered by Google’s Gemini 3 Flash model for creating novels, books, and short story collections.

Features 🤖 Autonomous Writing: The agent plans and executes creative writing tasks independently 📚 Multiple Formats: Create novels, books, or short story collections ⚡ Real-Time Streaming: See the agent’s thinking and writing appear as it’s generated 💾 Smart Context Management: Automatically compresses context when approaching token limits 🔄 Recovery Mode: Resume interrupted work from saved context summaries 📊 Token Monitoring: Real-time tracking of token usage with automatic optimization 🛠️ Tool Use: Agent can create projects, write files, and manage its workspace 🧠 Advanced Thinking: Uses Gemini’s thinking mode for better reasoning

What can you build with one HTML file and an LLM? A lot more than you think. This post shows hard-won patterns from 150+ real tools, showing how to skip frameworks, exploit browser primitives, and build projects fast with copy/pasteable code.

Stay informed with AI-summarized top stories from Hacker News. TL;DR for devs, ELI5 for everyone.

Open-source platform to build and deploy AI agent workflows. - simstudioai/sim

Design agent workflows visually on a canvas—connect agents, tools, and blocks, then run them instantly.

A tool to snap pixels to a perfect grid. Designed to fix messy and inconsistent pixel art generated by AI. - Hugo-Dz/spritefusion-pixel-snapper

Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation. - CHATS-lab/verbalized-sampling

Open-Source Memory Engine for LLMs, AI Agents

What is Memori Memori enables any LLM to remember conversations, learn from interactions, and maintain context across sessions with a single line: memori.enable(). Memory is stored in standard SQL databases (SQLite, PostgreSQL, MySQL) that you fully own and control.

Why Memori?

One-line integration - Works with OpenAI, Anthropic, LiteLLM, LangChain, and any LLM framework SQL-native storage - Portable, queryable, and auditable memory in databases you control 80-90% cost savings - No expensive vector databases required Zero vendor lock-in - Export your memory as SQLite and move anywhere Intelligent memory - Automatic entity extraction, relationship mapping, and context prioritization

Fara-7B is Microsoft’s first agentic small language model (SLM) designed specifically for computer use.

With only 7 billion parameters, Fara-7B is an ultra-compact Computer Use Agent (CUA) that achieves state-of-the-art performance within its size class and is competitive with larger, more resource-intensive agentic systems.

AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that’s as simple as writing Pandas code - lotus-data/lotus

LOTUS is an open-source query engine that makes programming as easy as writing Pandas and optimizes your programs for up to 400x speedups.

Run Qwen LLMs locally in your browser with WebGPU. Zero installation, instant AI chat.

flashcards in a private podcast feed. Knowledge in Audio format.