A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

let your agent control your phone

DeepSeek-V4-Flash-0731 284B inference in ~30 GB of RAM on any M-series MacBook

OpenOPC: Build Your Personal AI-Native Company — Self-Built, Self-Run, Self-Grown

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

A meta-skill plugin for Nous Research's Hermes AI agent that watches your workflows and automatically turns them into reusable skills. Every time you work with Hermes and solve something — setting…

Pi extension for async subagent delegation with truncation, artifacts, and session sharing

AI 短剧制作的 skill 集合：拆角色、出设定图、排大纲 | Agent skills for AI short-drama production — character bibles, model sheets, adaptation outlines. Runs in Claude Code & codex.

Configure DeepSeek as a native Codex subagent with automated setup and verified routing.

Create, refactor, audit, migrate, and validate Codex agent skills

Claude Fable as an orchestrator for Opus, GPT and Grok

Orchard: An Open-Source Agentic Modeling Framework

The best ChatGPT that $100 can buy.

Desktop app that records your on-screen work session and uses the GitHub Copilot CLI to reconstruct it as an intent + ordered steps, then builds a reusable Skill or Automation for Microsoft Scout, …

Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code…

Codex-native architect orchestration with Luna and Terra implementation lanes and mandatory fresh Sol review.

OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security

⚔️ Web Hacker's Weapons / A collection of cool tools used by Web hackers. Happy hacking , Happy bug-hunting

TokenHub gives enterprises a private gateway to unify AI model access and governance, making every request controllable, traceable, and attributable.

FDE（前沿部署工程师）从零入门指南（基于范冰《增长黑客》原书框架）

🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex…

Enterprise AI support-ticket workbench with traceable D01-D10 implementation and docs

Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull requests with deterministic QA and ensemble code review.