Explore the directory

A platform for building stateful AI agents with long-term memory that can learn and improve over time, usable from a terminal, desktop and web apps, or a TypeScript SDK.

• Agent frameworks
• Agent memory

A simple, open Markdown format for giving AI coding agents project-specific context and instructions, like a README aimed at agents rather than people.

• Agent skills

An open-source, self-hostable workflow automation platform, positioned as an alternative to Zapier, whose integrations double as MCP servers usable from Claude Desktop, Cursor or Windsurf.

• MCP servers
• Workflow automation

A mobile app for running open-source generative AI models fully on-device, for exploring, trying and evaluating on-device LLMs and other generative AI features offline.

• Models
• Inference

An autonomous multi-agent system for penetration testing that plans and runs security testing steps inside an isolated Docker sandbox, with specialist agents for research, development and infrastructure work.

• Security

A full-stack admin development platform built with Vue3 and Gin (Go) that includes JWT auth, RBAC via Casbin, dynamic routing and menus, code and form generators, and built-in MCP and skills management for AI-assisted development.

• Web frameworks
• Backend

A tool that distills a person's experience, judgment, voice and working style, from messages, documents and interviews, into a reusable profile packaged as an Agent Skill for AI agents and bots.

• Agent skills

A Chinese-language collection of tutorials and hands-on notes on large language model engineering, covering training, inference, compression, evaluation and deployment techniques.

• Tutorials

TOON is a compact, human-readable text encoding of the JSON data model, designed to use fewer tokens than JSON when passed to a language model while keeping structure easy to parse and validate.

• CLI tools
• Libraries

A curated collection of more than 160 specialized Claude Code subagents across ten categories, each a purpose-built AI assistant for a specific development task.

• Agent skills
• Curated lists

An SDK for building browser agents that extract data from and interact with any website, using Playwright-style methods across TypeScript, Python and Go.

• Browser automation

A collection of specialized Claude Code subagents, skills, hooks and rules that organizes a single Claude Code session into a coordinated game development studio.

• Agent skills

A CLI and library for evaluating and red-teaming LLM-based applications, comparing model providers side by side and scanning for security vulnerabilities from the command line or CI/CD.

• AI evals
• Security

A PyTorch implementation of the Vision Transformer (ViT) for image classification, plus many published variants and extensions of the architecture.

• Models

A curated collection of ready-to-use n8n workflow templates for services such as Gmail, Telegram, Slack, WhatsApp and OpenAI, covering AI agents, RAG chatbots, email automation and document processing.

• Workflow automation
• Curated lists

An open, lightweight specification for packaging AI agent capabilities as portable skill folders, containing instructions plus optional scripts, references and templates.

• Agent skills

An open-source, customizable RAG chat interface for asking questions over your own documents, aimed at both end users and developers who want to build their own retrieval pipeline.

• RAG

A lightweight Go framework for building cloud-native microservices, with a CLI that generates HTTP and gRPC code from Protobuf definitions.

• Backend

A fast, as-you-type fuzzy code-completion, comprehension and refactoring engine for Vim, built on multiple semantic completion engines and the Language Server Protocol.

• Editors

An open protocol, backed by the Linux Foundation, that lets AI agents built on different frameworks discover each other, negotiate how to interact, and collaborate securely on long-running tasks without exposing their internal state.

• Agent frameworks

A Mozilla.ai project that packages a large language model and its runtime into a single executable file, so it runs locally on most operating systems and CPU architectures with no installation.

• Inference

A collection of over twenty agent skills for Claude Code, Codex and similar AI agents that automate tasks such as WeChat article publishing and cover image generation.

• Agent skills

A document-parsing OCR model from Baidu built for one-shot, long-horizon parsing, with inference support through Transformers, vLLM and SGLang.

• Models

An open effort to reproduce DeepSeek-R1, providing scripts to train reasoning models with SFT and GRPO, generate synthetic training data, and evaluate the results.

• Models