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.
The most Token-efficient open-source AI Agent
| Date | Stars |
|---|---|
| 2026-07-31 | 1149 |
| 2026-08-04 | 1160 |
| 2026-08-06 | 1160 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
60.0
growth rate 0.00%/day
# OpenClacky [](https://github.com/clacky-ai/openclacky/actions) [](https://rubygems.org/gems/openclacky) [](https://www.ruby-lang.org) [](https://rubygems.org/gems/openclacky) [](LICENSE.txt) <p align="center"> <a href="README.md">English</a> · <a href="README_CN.md">简体中文</a> · <a href="README_JA.md">日本語</a> </p> > Contributing? Read **[CONTRIBUTING.md](./CONTRIBUTING.md)** before opening a PR. **The most Token-efficient open-source AI Agent.** OpenClacky matches Claude Code on capability at comparable cost, and saves significantly against other open-source agents (~50% vs OpenClaw, ~3× cheaper than Hermes). 100% open source (MIT), BYOK with any OpenAI-compatible model, built on two years of Agentic R&D and harness engineering. > Website: https://www.openclacky.com/ · Backed by **MiraclePlus · ZhenFund · Sequoia China · Hillhouse Capital** ## Why OpenClacky? Same task, how much do you pay? Under comparable agent workloads, OpenClacky saves a large amount of Token spend compared to mainstream alternatives. | Agent | Relative cost | Notes | |---|---|---| | **OpenClacky** | **~0.8** | 16 tools · ~100% cache hit · subagent routing | | Claude Code | 1.0× (baseline) | World-class harness, closed-source subscription | | OpenClaw | ~1.5× | Comparable harness agent | | Hermes | ~3× | 52 built-in tools — schema bloat ~3–4× | *Numbers are averages measured on internal common agent tasks, using Claude Code as the baseline. Full benchmark reports will be published on GitHub.* ## Feature comparison Core agent capability is roughly on par across the field — the real differentiators are **cost, openness, Skill evolution, and integrations**. | Feature | Claude Code | OpenClaw | Hermes | **OpenClacky** | |---|:---:|:---:|:---:|:---:| | Token cost | 1.0× | ~1.5× | ~3× | **~0.8** | | Open source | ❌ Closed | ✅ Open | ✅ Open | ✅ MIT | | BYOK / model freedom | ❌ Anthropic only | ✅ | ✅ | ✅ | | Skill self-evolution | ❌ | ❌ | ✅ | ✅ | | IM integration (Feishu/WeCom/WeChat/Discord/Telegram) | ❌ | ✅ | ✅ | ✅ | ## How we get the cost down Not by cutting features — by compounding the right choice at every layer. ### 1. Ultra-high cache hit rate Sessions never restart, double cache markers, **Insert-then-Compress** — the system prompt is never mutated, so compression still reuses the cache. **Measured cache hit rate: near 100%.** ### 2. Minimal tool set Only **16 core tools**. Capabilities are offloaded to the Skill ecosystem via a single `invoke_skill` meta-tool. Tool count is not the metric — task completion rate is. | OpenClacky | Claude Code | OpenClaw | Hermes | |:--:|:--:|:--:|:--:| | **16** | 40+ | 23 | 52 | ### 3. Idle-time auto-compression Go to a meeting, grab coffee — the agent compresses long context in the background and pre-warms the cache. Your first message back hits the cache directly. **Cold-start first-token cost reduced by 50%+.** ### 4. BYOK — you pick the model, you set the cost Any OpenAI-compatible API, plug and play. Official direct, aggregate routing, compatible relays — the choice is 100% yours. Use Claude for code, auto-route subtasks to DeepSeek, save another chunk of tokens. Built on **2 years · 3 generations of agentic architecture · 6 core harness engineering decisions**. ## Skills — the soul of the agent - **Invoke with `/`** — instant browse, fuzzy search, direct call. Hundreds of Skills at your fingertips. - **Create Skills in natural language** — just describe what you want; the agent drafts `SKILL.md`, breaks down steps, an
Excerpt of 9,723 characters
Read on GitHub
1.3k
379
123
11
9
7
5
5
5
4
3
2
2
2
Ikko Eltociear Ashimine · Japan
2
1
1
1
Octopus · Independent Developer · United States
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:342f19e7fdade953, desc:ai agent