Explore the directory

An open-source, native-Rust AI agent harness that runs as a GUI, CLI, headless process or web app from one binary, supporting multiple model providers, MCP, skills and plugins.

• Coding agents

A repository protocol and installer that gives a coding agent a compact entrypoint, a navigable map, durable plans, and mechanical validation, so intent and decisions stay in the repo instead of chat.

• Coding agents
• Agent skills

A tmux sidebar that tracks coding-agent sessions, showing agent state, repo breadcrumbs and quick jumps between panes for Amp, Claude Code, Codex and OpenCode.

• Coding agents
• Terminals

A GraphQL federation gateway that combined multiple GraphQL services into one API; the hosted platform has shut down and the gateway is now in maintenance mode.

• APIs

An agent harness and platform for building autonomous AI agents that orchestrate tools, memory and context, letting experts encode domain knowledge into reusable skills.

• Agent frameworks

A free, open-source collection of native macOS menu bar tools with a plugin marketplace, letting users build custom panels, automation workflows and system status widgets.

• Desktop utilities

A C++ engine for deploying video analytics and on-device vision-language models to edge hardware such as Sophon, Rockchip and x86, with orchestration, alarms and benchmarking.

• Inference

An article and companion website that walks through writing a minimal TypeScript coding agent, called nano-pi, from scratch, with source code that fills in as you read and a step-by-step execution trace.

• Tutorials

An MCP server that connects to Garmin Connect and exposes a user's fitness and health data, such as activities, sleep, training load and gear, to Claude and other MCP clients.

• MCP servers

A single Python interface for running and evaluating AI agents built with different frameworks such as Agno, Google ADK, LangChain, LlamaIndex, the OpenAI Agents SDK, and smolagents.

• Agent frameworks
• AI evals

oh-my-agent is a skill pack and harness for AI coding agents that verifies their work with stop-hook test gates, artifact checks, and an independent judge, instead of trusting the agent's own summary.

• Agent skills
• AI evals

A curated knowledge base about atomic, image-based Linux systems, collecting introductory writing, talks and a list of immutable and declarative distributions.

• Curated lists

A tool that checks every structural or behavioral claim an AI makes against ground truth with deterministic tools, so a claim about a binary, an API, or a piece of code only counts once it is verified rather than asserted.

• AI evals
• Testing

An embeddable version of Pure Data that lets applications run Pure Data patches as an audio synthesis engine, with bindings for several languages.

• Libraries

A must-read paper list on knowledge editing for large language models, tracking surveys, benchmarks, and techniques for updating a trained model's knowledge without full retraining.

• Papers

A multi-agent orchestrator that turns a described task into a full PROMPT.md plan, then plans, executes, and reviews it in an isolated git worktree, with a human approval gate wherever the user wants one.

• Coding agents
• Agent frameworks

A wearable and phone app that connects to a user's own Claude Code, Codex, Grok, or Cursor session running on their Mac or PC, letting them view it live, send tasks, and drive it remotely by voice.

• Coding agents

A GitHub Action that runs the Codex CLI in a workflow behind a secure proxy to the Responses API, with configurable filesystem and network permissions, for building things like a custom pull-request review bot.

• Coding agents
• CI/CD

A curated collection of autonomous and multi-agent LLM-powered projects, spanning applications, advanced components, frameworks, benchmarks, and platforms, with a browsable companion website.

• Curated lists

A CLI session manager for multiple AI coding assistants, including Claude Code, Gemini CLI, Codex CLI, and Copilot CLI, run in parallel across git worktrees without needing tmux.

• Coding agents

An AI workflow automation platform that combines YAML-defined workflows, actions, agents, and conversational channels, with tools, MCP, memory, and retrieval-augmented generation, in one runtime.

• Agent frameworks
• Workflow automation

A modern web interface for chatting with local LLMs served by Ollama, with local chat history, Markdown rendering, dark mode, and a hosted version plus a Docker Compose setup.

• Inference

An open standard and CLI for shared agent learning, letting AI coding agents query and contribute a structured store of prior fixes and workarounds so they stop rediscovering each other's mistakes.

• Agent memory

A curated list of research papers and resources on agentic AI in healthcare, covering medical image analysis, EHR manipulation, patient dialogue, drug discovery, and healthcare administration, tied to a published survey.

• Curated lists
• Papers