Open-source projects tagged “llm”

A public collection of Agent Skills: instruction folders with scripts and resources that Claude loads to handle specialized tasks.

Open-source Python web crawler that turns any website into clean, LLM-ready Markdown for RAG, AI agents and data pipelines.

Open-source AI platform that turns any topic or document into an interactive classroom with AI teachers and classmates.

A macOS menu bar app and local gateway that lets Claude Code, Codex, Gemini CLI and other agents use any model or subscription you have.

Apache Maka (Incubating) is an agent workspace for running AI coding tasks locally, with a full append-only record of every model message, tool call and permission decision.

Self-hosted AI assistant and persistent bot platform where you choose the model and sandbox, available on web, desktop, iPhone and Android.

Open-source chat interface where an AI agent answers questions with text, native components, or custom interactive UI such as charts, calculators and maps.

Local-first AI e-book reader for desktop and mobile, with RAG chat, semantic search, highlights, TTS and WebDAV sync.

A Zotero plugin that lets you chat with one PDF, several PDFs, or your whole library, with clickable citations and optional fully local models.

A Chrome new-tab extension where Claude reads your browsing history and builds a fresh, personalized homepage each day.

A standalone macOS and Windows desktop app that wraps the Pi AI coding agent with a GUI, so you can run it without terminal setup.

ASPIRE is a research framework where coding agents iteratively write and refine sensorimotor skills for robot manipulation tasks in simulation and on real robots.

Pi, the coding agent, compiled ahead of time to native machine code so it starts faster and uses less CPU than Pi on Bun or Node.

An open source AI reader for articles and PDFs that answers questions about selected text in the margin, with citations.

A Python benchmark that measures how well LLMs solve the Bulls and Cows number-guessing game, using LiteLLM to reach many model providers.

A Cloudflare Worker that serves one AI-generated markdown essay per domain per UTC day, cached at the edge.