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.

Multiplayer AI: Bring your team and agents together

01Result

preset-io/agor ↗

preset-io/agor AI coding statistics: 56.8%

of 1,385 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
56.8% agent · top contributor 65.4%32 contributors
team

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

787
agent commits
598
other considered commits
32
agent contributors
65.4%
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

786assisted
1autonomous

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
2026-0294.7%133
2026-03100%109
2026-0490.2%163
2026-0581.3%160
2026-0628.5%291
2026-0747.6%164
2026-0835.8%274
2026-0917.6%91

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic78456.6%
GitHub CopilotGitHub40.3%
OpenAI CodexOpenAI20.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 72bf01ff on GitHubfeat(onboarding): connect Catalog tools in context and prefer existing SlaClaude Code
  • 1e921f6a on GitHubBlog: Meet Blake -- Guest Post from Preset's AI Deal Desk Enforcer (#2599)Claude Code
  • a555a6fa on GitHubfix(ui): stop a Home click from wedging the app shell (#2606)Claude Code
  • 1e921f6a on GitHubBlog: Meet Blake -- Guest Post from Preset's AI Deal Desk Enforcer (#2599)GitHub Copilot
  • c16e7268 on GitHubBlog: Meet Wendy, Preset's AI competitive intelligence analyst (#2593)GitHub Copilot
  • a23a011f on GitHubfeat(docs): add Microsoft Clarity analytics site-wide (#2029)GitHub Copilot
  • b45d82d1 on GitHubrefactor: keep git state on tasks and clean hook logs (#2149)OpenAI Codex
  • 840677bc on GitHubperf(ui): split AppEntityDataContext into Repo/User/Mcp granular contexts OpenAI Codex

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 window1,437
Merge commits removed−0
CI / dependency bots removed−52
Considered1,385

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 preset-io/agor

Scan another repository

Try