A workflow harness that helps AI coding agents plan, review, test, and ship safer code.
GitHub repository with 201 stars and 14 forks.
Language: Shell
Topics: ai-agents, ai-coding, claude-code, code-review, codex, developer-tools, engineering-workflow, security-audit, gstack, harness
Trending score 0.74, activity score 1.19, stars gained +1, forks gained +0.
2026-06-13: 201 stars and 14 forks.
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
GitHub repository with 508 stars and 27 forks.
Trending score: 2.20; stars gained: +18; forks gained: +0.
Language: Shell
Topics: add, agent-skills, ai-agents, ai-coding, architecture-driven-development, baseline-first
Control Room-first template for managing Hermes agents from one VPS agent to specialist teams and orchestrated workflows
GitHub repository with 571 stars and 93 forks.
Trending score: 2.09; stars gained: +20; forks gained: +2.
Language: Shell
Topics: agent-control-room, ai-agents, hermes-agent, multi-agent, vps
Reusable Skills for LLMQuant Agent, Claude Code, Claude.ai, Cursor, Hermes Agent, OpenClaw and Codex, grounded in LLMQuant Data
GitHub repository with 114 stars and 15 forks.
Trending score: 1.94; stars gained: +10; forks gained: +0.
Language: Shell
Topics: agent-skills, ai-agents, claude-code, codex, cursor, equity-research
Dryforge : New generation of harness engineering - Claude Code & Codex Plugin.
GitHub repository with 54 stars and 4 forks.
Trending score: 1.46; stars gained: +3; forks gained: +1.
Language: Shell
Topics: ai-agents, ai-assistant, claude, claude-code, claude-code-plugin, claude-plugin
Composable Agent Skills (Claude + OpenAI Codex) for taking an idea from fuzzy → validated → sequenced build → shipped — a manual tier (ideate, deep-dive, prompt-pack) and an autonomous tier (autopilot, build-loop).
GitHub repository with 51 stars and 6 forks.
Trending score: 1.36; stars gained: +22; forks gained: +1.
Language: Shell
Topics: agent-skills, ai-agents, ai-tools, anthropic, claude, claude-code
Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers.
GitHub repository with 205 stars and 17 forks.
Trending score: 0.91; stars gained: +1; forks gained: +0.
Language: Shell
Topics: agent-skills, ai-agents, computational-science, preregistration, reproducible-research
Skills for Real Engineers. Straight from my .claude directory.
GitHub repository with 127,240 stars and 11,114 forks.
Trending score: 5.88; stars gained: +2,576; forks gained: +217.
Language: Shell
🐹 Clean, uninstall, analyze, optimize, and monitor your Mac from the terminal.
GitHub repository with 55,740 stars and 1,940 forks.
Trending score: 3.74; stars gained: +101; forks gained: +13.
Language: Shell
Topics: analyzer, appcleaner, clean, cleaner, cleaner-cli, cleaner-script
GitHub repository with 1,510 stars and 71 forks.
Trending score: 3.33; stars gained: +70; forks gained: +4.
Language: Shell
Reimplementing Git in Rust. Like a boss.
GitHub repository with 302 stars and 20 forks.
Trending score: 3.26; stars gained: +40; forks gained: +3.
Language: Shell
Plan and autonomously build a software task end-to-end. One ready-to-paste /goal, adaptive phase count, memory preload + writeback, 3-strike self-healing recovery. Works on Claude Code and Codex.
GitHub repository with 444 stars and 27 forks.
Trending score: 3.25; stars gained: +96; forks gained: +6.
Language: Shell
原样镜像官方 Codex 桌面应用:每 15 分钟探测、SHA256 可校验、国内直连可达,附 macOS Sparkle 增量更新源 | Verbatim, verifiable mirror of the official Codex desktop app — probed every 15 min, China-reachable, with a Sparkle delta-update feed.
GitHub repository with 650 stars and 38 forks.
Trending score: 3.20; stars gained: +58; forks gained: +3.
Language: Shell
Topics: codex-app, github-actions, installer-mirror, macos, microsoft-store, msix
The agent that grows with you
GitHub repository with 192,310 stars and 33,527 forks.
Trending score: 5.48; stars gained: +990; forks gained: +282.
Language: Python
Topics: ai, ai-agent, ai-agents, anthropic, chatgpt, claude
🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Claude Code / OpenClaw / Codex / Cursor / OpenCode / Qwen / Copilot / Hermes / Kimi & 17+ CLIs.
GitHub repository with 64,146 stars and 7,157 forks.
Trending score: 5.14; stars gained: +1,086; forks gained: +115.
Language: TypeScript
Topics: agent-skills, ai-agents, ai-design, byok, claude-code-for-design, claude-design
The API to search, scrape, and interact with the web at scale. 🔥
GitHub repository with 132,084 stars and 7,777 forks.
Trending score: 4.77; stars gained: +854; forks gained: +24.
Language: TypeScript
Topics: ai, ai-agents, ai-crawler, ai-scraping, ai-search, crawler
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
GitHub repository with 82,613 stars and 9,527 forks.
Trending score: 4.64; stars gained: +171; forks gained: +18.
Language: Python
Topics: ai, ai-agents, context-engine, llm-apps, rag, retrieval-augmented-generation
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
GitHub repository with 17,391 stars and 2,665 forks.
Trending score: 4.61; stars gained: +767; forks gained: +155.
Language: JavaScript
Topics: ai-agents, ai-gateway, anthropic, chatgpt, claude, claude-code
754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 26 security domains · Apache 2.0
GitHub repository with 13,233 stars and 1,551 forks.
Trending score: 4.53; stars gained: +301; forks gained: +38.
Language: Python
Topics: ai-agents, claude-code, cybersecurity, incident-response, mitre-attack, penetration-testing