- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
01Result
study8677/repobrain ↗study8677/repobrain AI coding statistics: 41%
One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.
Agent share by month
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-02 | 10% | 10 |
| 2026-03 | 38.1% | 42 |
| 2026-04 | 47.2% | 72 |
| 2026-05 | 70.6% | 17 |
| 2026-06 | 44.4% | 9 |
| 2026-07 | 42.9% | 14 |
| 2026-08 | 28.6% | 14 |
| 2026-09 | 0% | 10 |
Peak month: 70.6%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 73 | 38.8% |
| Cursor Agent | Anysphere | 4 | 2.1% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
46d4b309on GitHubAdd freshness-aware ask, incremental quick refresh, rb doctor, and README Claude Codeb5024511on GitHubBump product version to 0.3.0 and CLI to 2.0.0 for RepoBrain releaseClaude Codecab5a7d7on GitHubRename functional identifiers from Antigravity to RepoBrainClaude Codeaefb94d1on GitHubdocs: fix documentation inaccuracies flagged by Codex in PR #115 (#117)Cursor Agentf32cb113on GitHubdocs: update hub/ layout in READMEs to match actual files (#116)Cursor Agenta1de58b1on GitHubdocs: update documentation to match current codebase (2026-08) (#115)Cursor Agent
04Method
What entered the denominator
The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.
Exclusion ledger
| Commits in window | 238 |
| Merge commits removed | −49 |
| CI / dependency bots removed | −1 |
| Considered | 188 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
Run the same detector locally.
Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.
npx qmmit-cli study8677/repobrain