Dataset: 2026-10-27-catalog-ai-v2
Ruleset: b2e8889c66f7
Scanned: 2026-10-27
Window: February–September 15, 2026

Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Secure, Fast, and Extensible Sandbox runtime for AI agents.

01Result

opensandbox-group/OpenSandbox ↗

opensandbox-group/OpenSandbox AI coding statistics: 13.6%

of 1,766 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

13.6% agent · top contributor 25%38 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

240

agent commits

1,526

other considered commits

agent contributors

25%

largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

238assisted

2autonomous

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

Peak month: 56.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	203	11.5%
GitHub Copilot	GitHub	23	1.3%
Cursor Agent	Anysphere	9	0.5%
Devin	Cognition	5	0.3%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

f4944838 on GitHubfix(sdk/kotlin): reject non-positive polling interval in checkReadyClaude Code
f9a1bbc8 on GitHubfix(sdk/kotlin): bound readiness polling sleepsClaude Code
0af3a463 on GitHubfix(javascript): stop readiness polling once the deadline is reachedClaude Code
3584c06f on GitHubDocument GHCR image registry publishingGitHub Copilot
2f4028c5 on GitHubAdd GHCR image publishing supportGitHub Copilot
9c1d4555 on GitHubPotential fix for pull request findingGitHub Copilot
16ea6e39 on GitHubosep: simplify to server-level secure runtime configurationCursor Agent
7c2e0a0c on GitHubfix(smoke): resolve pipe+heredoc stdin conflict in volume verificationCursor Agent
c3aecf16 on GitHubosep: address review feedback for OSEP-0004Cursor Agent
2a61b0d4 on GitHubfix(controller): select pool pods by ownerDevin
66eb7ab0 on GitHubfeat(controller): expose capacity metrics via OTLPDevin
5b29c5e7 on GitHubfix(server): make snapshot migration cold-start safeDevin

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	2,606
Merge commits removed	−751
CI / dependency bots removed	−89
Considered	1,766

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Devin commitsBrowse repositories with detected Devin signatures →Python AI coding statisticsCompare evidence across Python repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →

Reproduce this observation

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 opensandbox-group/OpenSandbox

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	14.4%	153
2026-03	6.8%	295
2026-04	13%	230
2026-05	34.3%	105
2026-06	56.2%	178
2026-07	4.1%	270
2026-08	4.1%	343
2026-09	3.6%	192