Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

SMILE software factory: a distributable, verified agent software factory (graph, loop, watcher, planning)

A platform for community discussion. Free, open, simple.

Cursor plugin specification and official plugins

Repeatable agents-plus-code workflows, packaged as one skill, stamped into any repo. Deterministic Python owns the graph; coding agents are bounded nodes inside it.

MacOS menu bar app for Brightspace. Never log in again. See every due date on one calendar. Click a course. Go straight there. Agents can read your courses and add assignments.

Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and …

The agent IDE that builds itself

Beads - A memory upgrade for your coding agent

This is a python API which allows you to get the transcript/subtitles for a given YouTube video. It also works for automatically generated subtitles and it does not require an API key nor a headles…

like netcat, but over Tailscale's data plane, without Tailscale's control plane

A spy satellite simulator in your browser, except the data is real. Live open source spatial intelligence on a photorealistic 3D globe.

Google Workspace in your terminal.

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

DeepSeek Harness: Everything is a Plugin.

You don't write AGENTS.md. You train it with gradient descent.

Kun's dotfiles for agentic engineering

Desktop app to manage markdown knowledge bases

Agent skill: adaptive X-only briefing of what happened + public opinion + debates

CLI security is broken. The packaging layer is where we fix it.

HTML is the new markdown. Lavish is the new editor for your HTML artifacts.

A collective list of free APIs

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

Agent skill that mines your repo's history to draft a VISION.md, stress-tests it with hard hypotheticals, and iterates with you on an interactive review board.

Talk to one agent. Ship with a crew.

Manage worktrees without managing worktrees.