Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

Money-saving guide to AI coding tools: free tiers, discounts, referral credits & open-source alternatives. 省钱指南。

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

A Streamlit-based chat app for LLMs with plug-and-play tool support via Model Context Protocol (MCP), powered by LangChain, LangGraph, and Docker.

This project provides a toolset to crawl websites wikis, tool/library documentions and generate Markdown documentation, and make that documentation searchable via a Model Context Protocol (MCP) server, designed for integration with tools like Cursor.

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

One governed graph for AI agents — GraphQL + MCP over your databases, files, APIs, and code

let any ai agent use the local browser

Transform your codebase into an intelligent knowledge base for AI-powered development with Cursor IDE, Google AntiGravity, and MCP-enabled assistants

AI Skills That Actually Do Things — 中文優先的 Claude Code / Codex agent skills 合集 · Reusable bilingual skills for any LLM workflow

蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harness plugin and an MCP server.

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

A Swift reimplementation of a Claude Code-style coding agent, built stage by stage to explore what makes coding agents work

A system monitoring tool that exposes system metrics via the Model Context Protocol (MCP). This tool allows LLMs to retrieve real-time system information through an MCP-compatible interface.

Telegram MCP gateway for AI agents: 8 tools, multi-tenant HTTP/stdio, MTProto

Browser automation MCP server for Claude, powered by Puppeteer.

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

Notes for you, Memory for your agents. / 内置 Deepseek harness Agent / 适用 办公 & 写作 & Coding

Anti-detect browser automation CLI & Skills for AI agents — Camoufox-powered fingerprint spoofing, no bot-detectable Playwright leaks

Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search.

Unified aelf skills hub for discovery, routing, bootstrap, and health checks across OpenClaw, Codex, Cursor, and Claude Code.

From-scratch, byte-matching decompilation of Super Mario 64 DS (sm64ds decomp) into C, with a live progress atlas and matching tools.