Stars
File-based message queue for local agent-to-agent communication (Maildir-style)
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.
Macro is a unified interface for email, messages, tasks, calls, agents, pull requests, docs, crm — linked together with shared AI memory.
NextPlaid, ColGREP: Multi-vector search, from database to coding agents.
Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing.
Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS.
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
The AI toolkit for building reliable browser automations
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
The lightest AI sandbox. A process-based sandbox for Linux, no container, no VM, no privilege, no prompt injection
AI agents running research on single-GPU nanochat training automatically
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
Proof SDK: open-source collaborative editor, provenance model, and agent HTTP bridge
This is the client for viewing traces captured by the XMLUI engine in xsVerbose mode and generating Playwright tests from traces
Calysto Hy, a Jupyter kernel for Hy using MetaKernel
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured
A Claude or Codex skill for deliberate skill development during AI-assisted coding
A community trust management system based on explicit vouches to participate.
Matchlock secures AI agent workloads with a Linux-based sandbox.
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.