Starred repositories
An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes.
Meta-Framework of Spatiotemporal Composability
DeepSeek Harness: Everything is a Plugin.
OSS-Fuzz - continuous fuzzing for open source software.
Archived snapshot of Thinking-with-Visual-Primitives
ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more.
Resources from my talk "Hacking the RP2350" at 38C3
An open-source user mode debugger for Windows. Optimized for reverse engineering and malware analysis.
Skills for Real Engineers. Straight from my .agents directory.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-rep…
Production-grade engineering skills for AI coding agents.
use your console controller to play claude code
Render Mermaid diagrams in your terminal or Python app
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
WeChat iLink Bot SDK for Node.js and Python — zero-config agent integration
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
Synapse: Matrix homeserver written in Python/Twisted + Rust
🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.
Headless CLI client for stateful Agent Client Protocol (ACP) sessions
A structured 5-dimension scoring framework for evaluating open-source AI projects from a VC investment perspective. Maintained by Lucy Chen, EIR at Zoo Capital (Singapore, $2B+ AUM).
A self hosted virtual browser that runs in docker and uses WebRTC.
这是一个为您定制的全网新闻聚合skill,支持多个信息源，支持深度获取，能够阅读文章正文并提供有理有据的深度解读。
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
orchestration layer for autonomous AI agents — using Linear or GitHub issues as your control plane
Autonomous task orchestrator for Kiro + Claude specs.