Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack
| Date | Stars |
|---|---|
| 2026-07-24 | 1056 |
| 2026-07-25 | 1056 |
| 2026-07-28 | 1057 |
| 2026-07-30 | 1057 |
| 2026-08-08 | 1064 |
| 2026-08-17 | 1073 |
| 2026-08-18 | 1073 |
| 2026-08-20 | 1088 |
| 2026-08-21 | 1093 |
| 2026-08-22 | 1094 |
| 2026-08-25 | 1095 |
| 2026-08-26 | 1096 |
| 2026-08-27 | 1097 |
| 2026-08-28 | 1100 |
| 2026-08-29 | 1101 |
| 2026-08-30 | 1103 |
| 2026-08-31 | 1107 |
| 2026-09-01 | 1110 |
| 2026-09-02 | 1113 |
| 2026-09-03 | 1115 |
| 2026-09-04 | 1114 |
| 2026-09-05 | 1115 |
| 2026-09-06 | 1116 |
| 2026-09-07 | 1118 |
| 2026-09-08 | 1118 |
| 2026-09-09 | 1119 |
| 2026-09-10 | 1120 |
| 2026-09-11 | 1124 |
| 2026-09-12 | 1126 |
| 2026-09-13 | 1127 |
| 2026-09-16 | 1129 |
| 2026-09-17 | 1131 |
| 2026-09-18 | 1131 |
| 2026-09-19 | 1132 |
| 2026-09-20 | 1134 |
Today
+2 stars today
This week
+7 stars this week
This month
+41 stars this month
Momentum
0.0
growth rate 0.62%/day
<p align="center"> <strong>English</strong> | <a href="docs/i18n/README.zh-CN.md">简体中文</a> | <a href="docs/i18n/README.ja-JP.md">日本語</a> | <a href="docs/i18n/README.ko-KR.md">한국어</a> | <a href="docs/i18n/README.vi-VN.md">Tiếng Việt</a> | <a href="docs/i18n/README.pt-BR.md">Português</a> | <a href="docs/i18n/README.es.md">Español</a> | <a href="docs/i18n/README.de.md">Deutsch</a> | <a href="docs/i18n/README.fr.md">Français</a> | <a href="docs/i18n/README.hi.md">हिंदी</a> </p> <div align="center"> <a href="https://flowser.ai"> <img src="assets/flowser-logo.svg" alt="Flowser" width="120"> </a> *Built by world-class engineers, for vibecoders at*<br> *[flowser.ai](https://flowser.ai) — AI Agents with computers for GTM* <br> # vibecode-pro-max-kit <br> <p align="center"> <img src="https://media.tenor.com/q_5em_iLaxoAAAAC/tanjiro-i-water-style.gif" alt="Flow like water" width="480"> <br><br> <em>"Total Concentration — Spec Breathing, Tenth Form: the Vibe Flow never breaks."</em><br> <strong>— Tanjiro Kamado</strong> </p> *Drop this into any project. Your AI agent gets a complete plan-first dev process — 7 gated phases, self-healing check loops, and autopilot that runs start to finish without losing its place.* <table align="center"> <tr> <td width="50%" valign="top"><strong>📦 One-command install</strong><br>One <code>curl</code> line drops it into any project. It detects new vs. returning users and never overwrites your files.</td> <td width="50%" valign="top"><strong>🌐 Works everywhere</strong><br>Any tech stack, any language, and any AI coding agent — Claude Code, Codex, Cursor, Windsurf, Copilot, and more.</td> </tr> <tr> <td valign="top"><strong>🧭 RIPER-5 plan-first workflow</strong><br>7 gated phases (Research → Spec → Innovate → Plan → Validate → Execute → Update-Process) stop the agent from jumping straight to code.</td> <td valign="top"><strong>🚀 Autopilot mode (quick / fast / full)</strong><br>Start a hands-free run at any phase with a single phrase. Three lanes match the ceremony to the risk.</td> </tr> <tr> <td valign="top"><strong>🎯 <code>/goal</code> — the run-until-done token</strong><br>One copy-pasteable block keeps the agent running phase after phase without stopping — and resumes the run in a fresh session.</td> <td valign="top"><strong>🔁 PVL + EVL self-healing loops</strong><br>Plan-check-fix and test-check-fix loops find gaps, fix them, and re-check on their own — up to 10 cycles each.</td> </tr> <tr> <td valign="top"><strong>🔍 vc-autoresearch</strong><br>A reusable find-gaps → fix → repeat loop you can point at plans, tests, specs, docs, or evals.</td> <td valign="top"><strong>🧪 Feasibility probes</strong><br>Test-before-you-build verdicts (VIABLE / NOT-VIABLE) before the agent commits to any design approach.</td> </tr> <tr> <td valign="top"><strong>🎛️ Smart strategy picker</strong><br>Before each phase it weighs one agent vs. many vs. a coordinated team — with cost estimates — and picks the cheapest that fits.</td> <td valign="top"><strong>🧮 Smart model use</strong><br>The expensive model only writes code; the cheaper model does everything else. Lower cost, same quality.</td> </tr> <tr> <td valign="top"><strong>🤔 Intent clarification</strong><br>When a request is vague, the agent asks a few sharp questions up front instead of guessing and building the wrong thing.</td> <td valign="top"><strong>🛡️ 36 validators</strong><br>Mechanical correctness checks — not opinions — guard the kit's own structure and catch drift before it ships.</td> </tr> <tr> <td valign="top"><strong>🏗️ Phase programs</strong><br>Large projects are split into independent phases with quality gates between them, so big work doesn't fall apart.</td> <td valign="top"><strong>🔀 Programs that reshape themselves</strong><br>As it learns, the agent inserts new phases, reorders work, and skips blocked steps — the plan adapts on the fly.</td> </tr> <tr> <td valign="top"><strong>🧠 Never loses its pla
Excerpt of 95,623 characters
Read on GitHub
89
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9ac0026d8bb50971, topic:ai-agents, topic:agentic, readme:ai agent
matched fp:9ac0026d8bb50971, topic:llm
matched fp:9ac0026d8bb50971, topic:developer-tools, topic:vibe-coding, readme:coding agent
matched fp:9ac0026d8bb50971, topic:prompt-engineering