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.

ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.

01Result

Osmantic/ODS ↗

Osmantic/ODS AI coding statistics: 28.4%

of 3,404 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
28.4% agent · top contributor 30.6%32 contributors
org-wide

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

966
agent commits
2,438
other considered commits
32
agent contributors
30.6%
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

966assisted
0autonomous

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
2026-0296.3%27
2026-0366.7%598
2026-0468.9%489
2026-0520.9%339
2026-067.5%133
2026-0711%653
2026-080.8%240
2026-095.3%925

Peak month: 96.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic95928.2%
OpenAI CodexOpenAI70.2%
Cursor AgentAnysphere10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 3f209126 on GitHubfix(cli): write preset export archives owner-onlyClaude Code
  • 3ba27ab8 on GitHubfix(update): let rollback find the backup ods update just wroteClaude Code
  • e783c207 on GitHubfix(env): append .env keys on their own line when the file lacks a final nClaude Code
  • 2e8446ec on GitHubfix: align manifest schema validator with service manifests (#1578)OpenAI Codex
  • 39164d8c on GitHubfix(perplexica): keep switchboard installs on stable model route (#1990)OpenAI Codex
  • ff50dde9 on GitHubfix(installer): cap bundled service CPU limits (#1362)OpenAI Codex
  • 6378c548 on GitHubfix(installer): start SearXNG for web search and Perplexica, not only --reCursor 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 window4,942
Merge commits removed−1,522
CI / dependency bots removed−16
Considered3,404

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 Osmantic/ODS

Scan another repository

Try