Browse Claude Code Skills, MCP Servers & AI Agents

The agent that grows with you. Trending agent framework from Nous Research with 168k+ stars.

Run large language models locally with a single command. 52M monthly downloads, 165K stars. Handles model downloading, quantization, GPU memory, and serves an OpenAI-compatible API.

Google's open-source terminal agent powered by Gemini 2.5 Pro with 1M token context. Free tier with 1,000 requests/day. Built-in tools for search, file operations, and web fetching.

OpenAI's lightweight terminal coding agent built in Rust. Reads, changes, and runs code locally. Supports multi-agent parallel execution via git worktrees.

Git-native terminal AI pair programming tool. Maps your entire codebase, auto-commits changes with descriptive messages, supports nearly every LLM. 4.1M+ installations.

Open-source terminal-native coding agent written in Go with a beautiful TUI. Supports 75+ AI model providers. Fast startup (<200ms), single binary, zero dependencies.

AI coding assistant skill for Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and Antigravity.

Local-first, open-source Claude Design alternative. 19 Skills. Works with Hermes Agent.

Cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, Hermes Agent. 81k+ stars.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. Flagship OpenClaw project.

Automates downloading manga from Kmoe as EPUB or MOBI files using concurrent workers.

Assesses OpenClaw skills against custom security policies for production readiness.

Publishes prepared content directly to Naver Blog from a local macOS environment.

Provides comprehensive physics support from intuitive conceptual explanations to advanced derivations.

Executes cryptocurrency trades, swaps, and cross-chain bridges across 24 blockchains.

Automates the packaging, pricing optimization, and publishing of Claude Code skills to ClawHub.

Generates AI-powered podcasts, explainer videos, and text-to-speech narrations from content.

Generates comprehensive Lean Canvas business models to validate startup hypotheses.

Generates structured product backlog items using the Why-What-Acceptance format.

Transforms raw meeting transcripts into structured, actionable summaries.

Builds comprehensive stakeholder maps using the Power/Interest grid.

Facilitates structured sprint retrospectives to surface team insights.

Generates comprehensive, stakeholder-aligned PRDs using a proven 8-section template.

Automates the installation, environment configuration, and messaging channel authentication for NanoClaw.