Explore the directory

An orchestration layer that adds an expert advisory board, 227 skills and 386 commands to Claude Code, Cursor or Codex, running local, open-core panels of routed specialists that deliberate before an agent team executes the result.

• Coding agents
• Agent skills

A curated list of MCP servers, tools, frameworks, datasets and research for applying agentic AI to cybersecurity work such as vulnerability scanning, threat modeling, reverse engineering and OSINT.

• Security
• Curated lists

A self-hosted AI agent harness distributed as a single Go binary that writes, sandbox-tests and repairs its own tools, then shares them with Claude Code, Codex and other MCP clients.

• Agent frameworks

lifxlan is a Python 3 library that controls LIFX lights over a local network by implementing the LIFX LAN protocol directly, without going through LIFX's cloud service.

• Libraries

A practical, opinionated handbook for building, evaluating, securing and shipping LLM agent systems, with templates, provider adapters, a skills catalog, coding-agent workflows and a curated catalog of existing agent projects.

• Tutorials
• Books

This project patches vLLM with hand-written SASS kernels so very large Mixture-of-Experts language models can run on consumer and workstation Blackwell GPUs that cannot otherwise fit their official checkpoints.

• Inference

guardrail is a code generator that turns OpenAPI and Swagger specification files into Scala and Java client and server code for frameworks such as akka-http, http4s, dropwizard and spring-mvc.

• APIs

A collection of example LLM projects built with Ollama's open-source models, covering retrieval-augmented generation, agent tooling and protocols, multi-agent systems, voice and vision use cases.

• Tutorials

An MCP server and CLI that automate the real Microsoft Excel application through its COM API, letting AI agents run Power Query, DAX, VBA and PivotTable operations while preserving formatting and macros.

• MCP servers

An open-source extension of the AWS Cloud Development Kit that provides sample, well-architected constructs for common generative AI patterns, such as retrieval-augmented generation, summarization and question answering on AWS.

• RAG
• Hosting

An open-source, unofficial multi-agent operating layer built around the Claude Code CLI that organizes 38 specialized business and engineering agents, runs routines, and consolidates their output into a dashboard.

• Coding agents
• Agent frameworks

Companion notebooks, reading notes and project files for a DeepLearning.AI short course that teaches Claude Code through examples covering a RAG chatbot, e-commerce data analysis and a Figma-to-app build.

• Tutorials

An MCP server that downloads YouTube subtitles with yt-dlp and exposes them to Claude, so an agent can summarize a YouTube video from its URL.

• MCP servers

An agent-native workspace for red-teaming web applications that combines a fast browser with direct control over HTTP traffic, so agents can navigate, capture, inspect, modify, replay and compare requests in one sandboxed, auditable interface.

• Security
• Browser automation

An AI automation layer for EasyEDA Pro that lets an agent read datasheets, draw schematics, lay out and route PCBs, adjust silkscreen and run design checks through the editor's own API.

• MCP servers
• Agent skills

A DeepSeek Harness plugin that gives an agent a persistent browser identity: a Chromium fork with engine-level fingerprint spoofing, saved profiles and logins between runs, Android device emulation, and residential proxy egress.

• Agent skills
• Browser automation

A bilingual collection of machine-learning, LLM, diffusion and agent interview cheat sheets for Chinese AI campus recruiting, auto-generated by the ARIS research-automation project, plus a CV-to-academic-homepage generator.

• Tutorials

Bonsai Image Demo is a command-line demo that generates images locally with the ternary or binary quantized Bonsai model, running on Apple Silicon via MLX or on NVIDIA GPUs on Linux and Windows through gemlite and HQQ kernels.

• Generative media

An intent-driven workflow orchestration tool for multi-agent AI development that plans, executes and verifies coding tasks across Claude Code, Codex, Gemini and other agent backends, with a self-reinforcing knowledge graph.

• Coding agents
• Agent frameworks

An MCP server that bridges AI models with TouchDesigner, letting agents create, modify and query nodes and run Python scripts inside a TouchDesigner project.

• MCP servers

An open-source Python SDK for orchestrating generative AI media pipelines across video, image and audio providers, with a built-in, verifiable provenance manifest for every output.

• Generative media

A runtime that wraps CLI coding agents such as Claude Code, Codex, Antigravity and OpenCode as persistent, programmable sessions, coordinating them in multi-agent councils and exposing them through an OpenAI-compatible endpoint, an MCP server and a dashboard.

• Coding agents
• Agent frameworks

A bilingual, engineering-first online textbook covering LLM agent fundamentals, tool use, memory, planning, retrieval-augmented generation, multi-agent systems, agentic reinforcement learning, evaluation, security and deployment.

• Tutorials
• Books

A relation-free graph-construction method for GraphRAG that eliminates LLM token costs during indexing, making graph-based retrieval-augmented generation faster over large corpora.

• RAG