GitHub repo leaderboard by stars, growth rate and activity.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
Extracted system prompts from Anthropic - Claude Fable 5.1, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. | JavaScript | 255,273 | last pushed Yesterday | |
| 2 | The agent that grows with you | Python | 243,904 | last pushed 21 hours ago | |
| 3 | The agent engineering platform. | Python | 146,036 | last pushed Yesterday | |
| 4 | 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman | Go | 104,585 | last pushed 2 days ago | |
| 5 | Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More | JavaScript | 93,582 | last pushed Yesterday | |
| 6 | CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies | Rust | 79,730 | last pushed 2 days ago | |
| 7 | Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server. | Python | 71,128 | last pushed 21 hours ago | |
| 8 | Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…) | JavaScript | 70,819 | last pushed 2 days ago | |
| 9 | OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering. | TypeScript | 68,866 | last pushed 21 hours ago | |
| 10 | Extracted system prompts from Anthropic - Claude Fable 5.1, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly. | JavaScript | 64,584 | last pushed Yesterday |
All · 11,474