Explore the directory

A multi-agent IT-operations automation platform that closes the loop from alert to AI diagnosis to a proposed fix, human approval on a phone, execution and verification, positioned as an open alternative to PagerDuty, Rundeck, Portainer and vCenter.

• Monitoring
• Workflow automation

A self-hostable, long-running AI agent for personal or team automation, with four-layer cognitive memory, a forgetting curve and contradiction detection, plus LLM-based approval for high-risk actions such as running commands or files.

• Agent memory
• Workflow automation

A lightweight Python CLI that estimates the inference memory a Hugging Face model needs, reading only its Safetensors or GGUF metadata over HTTP range requests rather than downloading the model.

• Inference
• CLI tools

A fast, local Rust MCP server and CLI that converts PDF, Word, PowerPoint, Excel, EPUB, HTML, images and audio or video files into clean Markdown for AI agents, without an API key.

• MCP servers
• RAG

A zero-copy, content-addressed build cache for Rust, C/C++, and CUDA that restores a compiler invocation's output instead of rebuilding it, sharing a cache locally or through S3.

• CI/CD

A lightweight bridge that exposes the Codex desktop app's user interface in a browser, running on Linux, Windows or Termux on Android.

• Coding agents

A private, identity-verified peer-to-peer network for AI agents, where each node publishes tools and models to the mesh and can discover and call what other nodes expose, with nothing reachable unless explicitly granted.

• Agent frameworks
• Networking

A Swift package that is an API-compatible drop-in replacement for Apple's Foundation Models framework, adding support for Core ML, MLX, llama.cpp and several hosted model APIs behind the same interface.

• Inference
• Libraries

An agentic AI security tool, developed at Capital One, that reasons forward from attacker-accessible entry points to identify which source-code defects are actually exploitable, then runs a falsification pass before reporting a finding.

• Security

The source and build pipeline behind the online book Coding for Economists, which teaches programming and data-science techniques to an economics audience.

• Tutorials
• Books

Pure-Python tools and research notes that reimplement X.com's internal web protocol, letting scripts read tweets and timelines, search, and post using an authenticated browser session's own tokens.

• APIs

A multi-agent framework that scales agent collaboration by treating a heterogeneous team of LLM agents as one unified recursive computation, connected by lightweight modules that exchange and refine shared latent state.

• Agent frameworks

A governed control plane and gateway for an organization's MCP servers, AI agents and skills, adding centralized OAuth authentication, discovery, access control and audit to otherwise scattered per-team integrations.

• MCP servers

A signed macOS menu-bar app that launches, supervises and monitors a local DeepSeek V4 or V4.1 inference server, downloading model weights and gating launches by a Mac's available RAM.

• Inference
• Desktop utilities

A self-paced bootcamp of tutorials and hands-on notebooks covering machine learning foundations, Ollama, large language models, retrieval-augmented generation, LangChain, LangGraph, fine-tuning, DSPy and AI agents built with CrewAI.

• Tutorials

A lightweight, container-free sandbox that wraps commands to block network access by default and restrict filesystem operations by configurable rule, and doubles as a permission manager for AI coding agents.

• CLI tools
• Security

A free, open-source desktop app that lets a developer write an AI agent skill once and sync it, through symlinks, to 32 supported coding tools such as Claude Code, Codex, Cursor and Gemini CLI.

• Agent skills

An educational, runnable Python reference implementation of a retrieval-augmented generation pipeline, splitting document loading, chunking, embeddings, FAISS and BM25 hybrid retrieval, reranking and answer generation into readable, replaceable modules.

• RAG
• Tutorials

A terminal and browser tool that reads a Claude Code or Codex session transcript and draws it as a live, replayable flow graph of the main agent, the agents it spawns, and the tools each one runs.

• Coding agents
• AI evals

A structured three-agent development process for Claude Code and other context-file-based tools, with an Architect that plans and deploys, a Builder that implements exactly the brief, and a Reviewer that catches what the Builder missed.

• Agent skills

A cross-platform desktop app, written in Rust and React, that iterates over combinations of local Ollama models, prompts and inference parameters and lets a user visually compare and A/B test the results.

• Inference
• AI evals

A curated list of slash commands, subagents, MCP servers and hooks packaged as installable Claude Code plugins, organized by category from workflow orchestration to security and compliance.

• Agent skills
• Curated lists

A community-built collection of study resources and mock practice exams for GitHub Certifications, such as GitHub Foundations and GitHub Advanced Security.

• Tutorials

An open-source remote procedure call system designed for multichip embedded systems and heterogeneous multicore SoCs, using plain C for remote functions and a small code footprint.

• Libraries