Directory

Explore the directory

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

6,821 listings

  • A Python library that integrates large language models such as ChatGPT into scikit-learn for text analysis tasks like zero-shot classification.

  • A set of skills for Claude Code and Codex that draft LinkedIn posts, comments and replies in the user's own voice and wait for approval before publishing.

  • Google Antigravity SDK

    antigravity.google

    A Python SDK for building AI agents powered by Google's Antigravity platform and Gemini models, with a stateful runtime that handles the agent loop.

  • A utility that keeps a Codex CLI installation's session files and local SQLite chat index aligned with the AI model provider currently configured.

  • Build with Claude

    buildwithclaude.com

    A discovery platform and plugin marketplace for Claude Code, letting developers browse and install community skills, agents, commands, hooks and plugins.

  • Expect

    expect.dev

    Expect is a skill that reads an agent's code changes, writes a browser test plan, and runs it with Playwright against a real, logged-in session to find regressions before they ship.

  • kagent

    kagent.dev

    A Kubernetes-native framework for building, deploying and managing AI agents as Kubernetes custom resources.

  • Observal

    observal.io

    A self-hosted registry and control plane for an organization's internal Skills, MCP servers and Agents, adding a discoverability layer and usage insights so teams reuse components instead of rebuilding them.

  • md2wechat

    md2wechat.cn

    A command-line tool built for AI agents that converts Markdown into WeChat official-account HTML, generating covers and article images, previewing results and creating drafts through discoverable JSON commands.

  • FlashRAG

    arxiv.org

    A Python toolkit for reproducing and developing retrieval-augmented generation research, bundling 36 preprocessed benchmark datasets and 23 published RAG algorithms behind one customizable pipeline framework.

  • Eagle

    nvlabs.github.io

    A family of frontier vision-language models from NVIDIA exploring data-centric training strategies for general multimodal understanding, long-context reasoning and embodied applications.

  • GithubStarsManager

    gsm.aminta.top

    An AI-assisted desktop app that syncs a user's starred GitHub repositories, automatically summarizes and categorizes them, and adds semantic search, release tracking and fork and gist management.

  • OpenDeepWiki

    github.com

    A self-hosted platform that turns Git repositories, ZIP archives, or local directories into a searchable, AI-generated documentation and chat knowledge base.

  • hyperresearch

    hyperresearch.ai

    A deep-research skill for Claude Code and OpenAI Codex that runs a multi-step research pipeline over many web sources, verifies citations and builds a persistent, searchable vault of prior findings.

  • A packaged Agent Skill that gives any AI coding tool supporting the Agent Skills format expert guidance on SwiftUI state management, view composition, performance and recent SDK changes.

  • Terramate

    terramate.io

    An open-source orchestration and code-generation engine that scales Infrastructure-as-Code projects using Terraform, OpenTofu, Terragrunt, or Kubernetes.

  • GoClaw

    goclaw.sh

    A multi-tenant AI agent gateway written in Go that rebuilds OpenClaw with multi-tenant PostgreSQL isolation, layered permission controls and native concurrency for deploying AI agent teams at scale.

  • An open-source Model Context Protocol server that gives Claude and other MCP-compatible AI agents access to LinkedIn profiles, companies, jobs and messages through a user's own logged-in browser session.

  • abtop

    github.com

    A terminal monitor for AI coding agent sessions, similar to htop, showing Claude Code, Codex CLI and OpenCode token usage, context-window percentage, rate limits, child processes and open ports in real time.

  • LazyCodex

    lazycodex.ai

    An agent harness for OpenAI Codex that adds project memory, planning, execution and verified completion on top of Codex sessions, installed through the OmO agent-harness project.

  • CodexGuide

    codexguide.ai

    A Chinese-language practical guide to using OpenAI Codex, covering setup across its CLI, desktop app, IDE extension, and cloud, plus workflows for real projects.

  • twinny

    twinny.dev

    An open-source AI coding assistant for VS Code that provides code completion, inline edits, chat, code review and commit messages against a model server the user controls, with no telemetry or sign-in.

  • CopilotChat.nvim

    copilotc-nvim.github.io

    A Neovim plugin that brings GitHub Copilot Chat into the editor, supporting multiple models, tool calling with manual or automatic approval, and a scriptable Lua API for automation.

  • OpenSumi

    opensumi.com

    A TypeScript framework for building AI-native IDE products, providing an extensible IDE core and an MCP client so an IDE built on it can use tools exposed by MCP servers.