Directory

Explore the directory

Tools, libraries, services and references, each reviewed before it goes public. 6,821 resources listed.

6,821 listings

  • RocksDB

    rocksdb.org

    An embeddable, persistent key-value store library optimized for flash and RAM storage, built for high write and read throughput at multi-terabyte scale.

  • minikube

    minikube.sigs.k8s.io

    A tool that runs a local, single- or multi-node Kubernetes cluster on macOS, Linux or Windows for developing and testing Kubernetes applications.

  • Onyx

    onyx.app

    An open-source AI platform that indexes more than 50 workplace applications to give LLMs and AI agents context about a team's own knowledge, alongside chat, deep research and custom agents.

  • A hands-on, Chinese-language tutorial for configuring, deploying and fine-tuning open-source large language models on Linux, covering more than 50 mainstream Chinese and international models.

  • AgentScope

    docs.agentscope.io

    A production-ready agent framework built around a ReAct reasoning-and-acting loop, a pluggable toolkit and model layer, and composable middleware, designed to work with increasingly capable models rather than constrain them with rigid orchestration.

  • skills

    skills.sh

    A command-line tool for installing and using AI agent skills from a Git repository, a URL or an archive, compatible with Claude Code, Codex, Cursor, OpenCode and dozens of other coding agents.

  • book-to-skill

    github.com

    A tool that converts a technical book PDF, document folder or other structured prose into a structured agent skill, so a coding agent loads only the relevant chapter on demand instead of the whole text.

  • ZeroClaw

    zeroclaw.com

    A self-hosted personal AI agent runtime, distributed as a single Rust binary, that connects to about twenty LLM providers and reaches the user through more than 30 channels such as Discord, Telegram, email and a custom CLI.

  • A free course that teaches how to build AI agents, moving from the basics of agents and LLMs through frameworks such as smolagents, LlamaIndex and LangGraph to a final, automatically evaluated project.

  • AionUi

    aionui.com

    An open-source Cowork platform where AI agents such as Claude Code, Codex and OpenCode work alongside the user on their own computer, with a built-in agent, scheduled automation and remote access from chat apps.

  • GitHub's official Model Context Protocol server, giving AI agents and assistants the ability to read repositories, manage issues and pull requests, analyze code and automate GitHub workflows through natural language.

  • go-zero

    go-zero.dev

    A cloud-native Go framework for building resilient web and RPC microservices, with a code generation tool that scaffolds services and clients from API definitions.

  • oh-my-codex

    oh-my-codex.dev

    A workflow layer for OpenAI's Codex CLI that keeps Codex as the execution engine while adding a repeatable plan-to-completion workflow, invoked through commands such as $plan, $team and $code-review.

  • Nacos

    nacos.io

    A dynamic service discovery, configuration management and service management platform for building cloud-native and microservices applications, with newer support for registering AI agent and MCP servers.

  • An independent, community-built library of more than 800 structured cybersecurity skills for AI agents, each mapped to security frameworks such as MITRE ATT&CK and NIST CSF, for authorized testing, defense and education.

  • oh-my-pi

    omp.sh

    A coding agent, forked from Mario Zechner's Pi, that wires IDE-level tooling such as language-server and debugger operations directly into its tool set and supports more than 60 model providers.

  • OpenClaude

    openclaude.gitlawb.com

    An open-source, terminal-first coding-agent CLI that works with OpenAI-compatible APIs, Gemini, GitHub Models, Ollama and other cloud or local model providers.

  • A library of reverse-engineered prompts and reusable templates for GPT-Image 2 and 2.5, browsable on a companion gallery site and packaged as reusable prompt skills for image generation.

  • A Claude Code plugin that runs OpenAI Codex from inside a Claude Code session, for reviewing code or handing off tasks to Codex without leaving the existing workflow.

  • Tabby

    tabbyml.com

    A self-hosted AI coding assistant offered as an open-source, on-premises alternative to GitHub Copilot, running without a separate database or cloud service and supporting consumer-grade GPUs.

  • Happy-LLM

    datawhalechina.github.io

    A systematic, free tutorial that teaches how large language models work by building one from scratch, from NLP and Transformer fundamentals through pretraining, fine-tuning, RAG, agents and reinforcement learning.

  • ChatDev

    arxiv.org

    A multi-agent orchestration platform that lets a user define agents, workflows and tasks through configuration rather than code, evolved from an earlier system that simulated a whole virtual software company.

  • Qdrant

    qdrant.tech

    A vector similarity search engine and vector database, written in Rust, with a production API for storing, searching and filtering vectors alongside their payload data.

  • Awesome Agent Skills

    officialskills.sh

    A curated collection of more than 1,000 agent skills contributed by development teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor and other agent harnesses.