ai-written commits — tracked daily since 2025
THE AI CODE INDEX
Which AI coding tool is actually winning? Daily commit volume, market share, and doubling time across 7 tools on all public GitHub repos.
§ 1 — total daily commit volume, all tools
fig. 01
85.9M commits · last 6 months · ▲ 827% vs prior span
latest complete day — aug 10 · 660k
§ 2 — market share of ai-written commits
fig. 02
§ 3 — the race for #2
fig. 03
cursor
55.2k/day · ▲ 29%
codex
2.4k/day · ▼ 15%
aider
194/day · ▼ 2%
gemini cli
56/day · ▼ 81%
claude code owns the index, so it's out of this grid — one shared scale for everyone else.
§ 4 — momentum, ranked
fig. 04
| no. | tool | momentum 30d | commits/day | doubles every | share |
|---|---|---|---|---|---|
| 01 | cursorfastest | ▲ 29% | 55.2k | 79 days | 8.4% |
| 02 | claude code | ▲ 1% | 602k | 3989 days | 91.2% |
| 03 | aider | ▼ 2% | 194 | — | 0.0% |
| 04 | codex | ▼ 15% | 2.4k | — | 0.4% |
| 05 | gemini cli | ▼ 81% | 56 | — | 0.0% |
01cursorfastest
▲ 29% · 55.2k/day · 79d to double · 8.4%
02claude code
▲ 1% · 602k/day · 3989d to double · 91.2%
03aider
▼ 2% · 194/day · — · 0.0%
04codex
▼ 15% · 2.4k/day · — · 0.4%
05gemini cli
▼ 81% · 56/day · — · 0.0%
§ 5 — the pr arena
fig. 05
fig. 05 — autonomous agent prs, all time
github copilot and devin don’t sign their commits, so they score zero in the charts above. zero there isn’t absence — it’s invisibility. this is their arena.
§ 6 — the open model layer
fig. 06
models — release snapshots (big stars, low velocity)
- mistralai/mistral-vibeMistral Vibe is a free, open-source AI assistant that lets developers have a conversation with their codebase directly from their computer's command line, using plain English to explore, edit, and manage code projects. It's built by Mistral, a leading European AI company, and runs on their own AI models.22/100Active4.8k★ · 625⑂
- deepseek-ai/DeepSeek-V3DeepSeek-V3 is a powerful open-source AI language model — similar to the technology behind ChatGPT — that can understand and generate text, answer questions, write code, and reason through complex problems. It was built by Chinese AI lab DeepSeek and is freely available for developers and companies to download, customize, and deploy in their own products.19/100Active104k★ · 16.7k⑂
- meta-llama/llamaThis is Meta's official release of Llama 2, a family of powerful AI language models that anyone — from individual developers to large companies — can download and run on their own systems. It provides the core model files and basic code needed to load and use these AI models, which range in size and capability, for tasks like answering questions, writing, and conversation.17/100Active59.6k★ · 9.8k⑂
- deepseek-ai/DeepSeek-R1DeepSeek-R1 is a family of open-source AI reasoning models that can solve complex math, coding, and logic problems by 'thinking through' problems step by step before answering. It matches the performance of OpenAI's most advanced reasoning model (o1) and is freely available for anyone to use or build on.3/100Active92.0k★ · 11.7k⑂
- zai-org/GLM-4.5—4.4k★ · 469⑂
runtime — where open-model energy lives
- MoonshotAI/kimi-codeKimi Code is an AI-powered assistant that lives in your computer's command line and acts like a tireless junior developer — it can read and modify your codebase, run programs, search the web, and make decisions on its own to complete tasks. It's built by Moonshot AI and connects to their Kimi AI models, though it can also work with other AI providers.54/100Hot6.4k★ · 1.0k⑂
- ollama/ollamaOllama lets anyone run powerful AI language models (like DeepSeek, Gemma, and Qwen) directly on their own computer, without needing cloud services or an internet connection. It works on Mac, Windows, and Linux, and comes with a simple interface so developers and non-technical users alike can chat with or build applications on top of these AI models locally.50/100Hot178k★ · 17.4k⑂
- ggml-org/llama.cppllama.cpp lets developers run AI language models (like the ones powering chatbots) directly on their own computers or servers, without needing expensive cloud services. It's a highly optimized software engine that squeezes AI models onto a wide range of hardware — from laptops to professional GPUs — with minimal setup.40/100Hot124k★ · 21.6k⑂
- unslothai/unslothUnsloth is a free, locally-run tool that lets you train and customize the latest AI models — like DeepSeek, Gemma, and Qwen — directly on your own computer, without sending data to the cloud. It provides a visual interface so you can fine-tune (teach an AI new skills using your own data) and run powerful AI models without relying on expensive third-party services.34/100Active70.4k★ · 6.4k⑂
the tools above run on these. open models don’t sign their commits, so this layer is repo traction — not usage share. anything else would be made up.
§ 7 — ecosystem adoption
fig. 07
config files in repos
sdk / package adoption
note: agents.md (an open format) beats every vendor-specific config file.
§ 8 — community pulse
fig. 08
fig. 08 — community pulse, 7 days
| tool | mentions | hn | github | |
|---|---|---|---|---|
| claude code | 463 | 99 | 0 | 364 |
| github copilot | 212 | 5 | 0 | 207 |
| codex | 95 | 0 | 0 | 95 |
| gemini cli | 28 | 2 | 0 | 26 |
| cursor | 20 | 0 | 0 | 20 |
| devin | 4 | 0 | 0 | 4 |
| aider | 2 | 0 | 0 | 2 |
§ 9 — intelligence brief
fig. 09
$ tail -f /var/log/gitfind/index.log
09:41:02 index sync completed — 660k commits counted across 5 of 7 tools
09:41:03 claude code leads the index at 91.2% of ai-written commits
09:41:04 cursor added 12.5k/day this month — biggest absolute gain
09:41:05 cursor is the fastest doubler — every 79 days at current pace
09:41:06 github copilot leads the pr arena with 2.4k agent prs — without signing a single commit
09:41:07 gemini cli down 81% this month — watching for a floor
09:41:08 █
form 27-b — subscription
THE TUESDAY BRIEFING
The repos that moved this week, why they matter, and what to watch next. One email. No noise.