Pulse
2026-09-18-v3.0
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.

An interface library for RL post training with environments.

01Result

openenv/OpenEnv ↗

openenv/OpenEnv AI coding statistics: 14.2%

of 471 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
14.2% agent · top contributor 40.3%11 contributors
org-wide

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

67
agent commits
404
other considered commits
11
agent contributors
40.3%
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

53assisted
14autonomous

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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020.7%137
2026-0312%25
2026-0434.6%26
2026-0566.7%33
2026-063.8%105
2026-074.3%92
2026-0822.7%22
2026-0961.3%31

Peak month: 66.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic4710%
Cursor AgentAnysphere204.2%
GitHub CopilotGitHub20.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 6f5e7c96 on GitHubRFC 008 slice 0b: registries, report schema, and severity policy (#1045)Claude Code
  • 07a0744c on GitHubRFC 008 slice 0a: core types, normalized manifest, and fixtures (#1044)Claude Code
  • 214be927 on GitHubRFC 008: detection table lists only implemented parsersClaude Code
  • a3ee7644 on GitHubfix(discovery): per-user cache with trusted open/atomic save (from #1011) Cursor Agent
  • ae179525 on GitHubfix(hooks): stop lint.sh from mutating the tree (from #1070) (#1163)Cursor Agent
  • 703ce323 on GitHubfix(envs): declare importable manifest app paths (from #1068) (#1164)Cursor Agent
  • d9f7718b on GitHubPin merged ThinkingBox reasoning effort supportGitHub Copilot
  • 8823fc79 on GitHubdocs: fix rendering issues post HF doc-builder migration (#743)GitHub Copilot

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 window639
Merge commits removed−121
CI / dependency bots removed−47
Considered471

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 →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 openenv/OpenEnv

Scan another repository

Try