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.
Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps.
| Date | Stars |
|---|---|
| 2026-07-24 | 1139 |
| 2026-07-25 | 1141 |
| 2026-07-28 | 1146 |
| 2026-07-30 | 1146 |
| 2026-07-31 | 1152 |
| 2026-08-06 | 1152 |
Today
— stars today
This week
+6 stars this week
This month
— stars this month
Momentum
51.0
growth rate 0.52%/day
<p align="center"> <img src="./assets/images/moai-adk-og.png" alt="MoAI-ADK" width="100%"> </p> <h1 align="center">MoAI-ADK</h1> <p align="center"> <strong>An Agentic Development Kit designed for Tokenomics</strong> </p> <p align="center"> English · <a href="./README.ko.md">한국어</a> · <a href="./README.ja.md">日本語</a> · <a href="./README.zh.md">中文</a> </p> <p align="center"> <a href="https://book.mo.ai.kr" target="_blank"><strong>Official Book: Practical Agentic Coding with Claude Code</strong></a><br> A hands-on harness engineering guide by the MoAI-ADK author — <a href="https://book.mo.ai.kr" target="_blank">book.mo.ai.kr</a> </p> <p align="center"> <a href="https://github.com/modu-ai/moai-adk/actions/workflows/ci.yml"><img src="https://github.com/modu-ai/moai-adk/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <a href="https://github.com/modu-ai/moai-adk/actions/workflows/codeql.yml"><img src="https://github.com/modu-ai/moai-adk/actions/workflows/codeql.yml/badge.svg" alt="CodeQL"></a> <a href="https://codecov.io/gh/modu-ai/moai-adk"><img src="https://codecov.io/gh/modu-ai/moai-adk/branch/main/graph/badge.svg" alt="Codecov"></a> <br> <a href="https://go.dev/"><img src="https://img.shields.io/badge/Go-1.26+-00ADD8?style=flat&logo=go&logoColor=white" alt="Go"></a> <a href="https://github.com/modu-ai/moai-adk/releases"><img src="https://img.shields.io/badge/Release-v3.0.1-blue.svg" alt="Release"></a> <a href="./LICENSE"><img src="https://img.shields.io/badge/License-Apache--2.0-blue.svg" alt="License: Apache-2.0"></a> </p> <p align="center"> <a href="https://adk.mo.ai.kr"><strong>Official Documentation</strong></a> · <a href="https://adk.mo.ai.kr/book">Book: Practical Agentic Coding with Claude Code</a> · <a href="https://discord.gg/Z7E7Mdc5aN">Discord</a> </p> --- > **"Tokenomics is a harness designed to make token consumption economical."** --- ## MoAI-ADK is a Tokenomics Harness MoAI-ADK (Agentic Development Kit) enables Claude Code to produce code, then makes that code reliable at predictable cost. A harness wraps the model from the outside. The model is a stochastic worker moving token by token — it remembers neither budget, nor quality bar, nor where the last session broke off. Cost ceilings, passing test suites, continuity that survives `/clear` — properties like these cannot be re-seeded by a prompt every turn; the system must enforce them from the outside. Every design decision serves one goal: token economics — the same quality for fewer tokens, higher quality for the same tokens. Which model to use, how deeply to reason, how to spend context — none of this is left to chance turn by turn; the system decides. It does not replace Claude Code. It only wraps, in structure, the parts Claude Code leaves to you — model routing, quality gates, cost control, session continuity. A single binary written in Go, it runs on macOS, Linux, and Windows with no extra dependencies. --- ## Why Tokenomics Token prices keep falling, but actual agent workflow spend rises. Agents spin through dozens to hundreds of steps to solve a single task, consuming proportionally more tokens. In usage-based pricing, this becomes the invoice; in subscription, it consumes the weekly quota shared by all models. ### Cost is determined by assignment, not unit price The DeepSWE leaderboard (113 tasks) demonstrates this problem. Even within the same Claude family and at the same max effort, per-task costs vary widely. | Model [max] | Pass@1 | Per-task cost | $/solved | Tokens/solved | Steps | |---|---|---|---|---|---| | claude-opus-4.8 | 59% | $13.22 | **$22.4** | 229k | 120 | | claude-fable-5 | 70% | $21.63 | $30.9 | 170k | 88 | | claude-sonnet-5 | 54% | $26.40 | **$48.9** | 396k | 268 | Sonnet 5 max is **more expensive than Opus 5 max per task** ($26.40 vs $13.22) while scoring lower (54% vs 59%). The cause is 268 steps — at max effort, retry loops explode. "Use a weaker model harder to save money" doe
Excerpt of 20,327 characters
Read on GitHub
2.1k
32
3
2
1
zerone0x
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f8f043ac8134a8ec, topic:ai-agent, topic:multi-agent, topic:agentic-ai
matched fp:f8f043ac8134a8ec, topic:ai-coding, topic:developer-tools, topic:vibe-coding