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.

Open GenAI Stack

01Result

ogx-ai/ogx ↗

ogx-ai/ogx AI coding statistics: 41.1%

of 850 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
41.1% agent · top contributor 52.7%27 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

349
agent commits
501
other considered commits
27
agent contributors
52.7%
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

349assisted
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
2026-0211.5%113
2026-0327.6%192
2026-0466.7%144
2026-0568.8%154
2026-0645.4%108
2026-0729.4%68
2026-0812.9%31
2026-0920%40

Peak month: 68.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic33739.6%
Cursor AgentAnysphere91.1%
GitHub CopilotGitHub30.4%
DevinCognition20.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • cea766a9 on GitHubfix(vector_io): compute usage_bytes from indexed chunks instead of leavingClaude Code
  • 016ed826 on GitHubfix(responses): report failed instead of completed when truncation=auto exClaude Code
  • 737d0a8a on GitHubfix(paper): pin bibliography citations to reproducible source snapshots (#Claude Code
  • eadbf55f on GitHubfix(vertexai): persist Gemini thought_signature across tool-call round triCursor Agent
  • 8b355bfb on GitHubfix(prompts): raise typed not-found errors to preserve HTTP keep-alive (#6Cursor Agent
  • 41474053 on GitHubrefactor!: remove tool_groups from public API and auto-register from proviCursor Agent
  • ce279576 on GitHubchore: dummy gpu ec2 runner workflow (#6102)GitHub Copilot
  • 96903175 on GitHubchore: Enable Hugging Face model caching for Vector IO integration tests (GitHub Copilot
  • 0f7a1447 on GitHubdocs: fix landing page hero command post-rename (#5651)GitHub Copilot
  • 3fcb5ac4 on GitHubfeat(cli): auto-detect web search providers in ogx letsgo (#6067)Devin
  • 4af4d0aa on GitHubfeat(docling): add do_ocr option (#6006)Devin

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 window994
Merge commits removed−0
CI / dependency bots removed−144
Considered850

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 ogx-ai/ogx

Scan another repository

Try