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.

Where people and agents build in tune.

01Result

tutti-os/tutti ↗

tutti-os/tutti AI coding statistics: 20.8%

of 3,660 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
20.8% agent · top contributor 56.5%27 contributors
team

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

761
agent commits
2,899
other considered commits
27
agent contributors
56.5%
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

761assisted
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
2026-0634.6%1018
2026-0718.8%1871
2026-087.6%768
2026-090%3

Peak month: 34.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic60916.6%
Cursor AgentAnysphere1544.2%
OpenAI CodexOpenAI30.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8fa59f86 on GitHubfix(agent): resolve extension setup, recovery, and capability regressions Claude Code
  • 8039a948 on GitHubfix(agent-gui): rewrite target setup description in user language (#2566)Claude Code
  • 7dc392ec on GitHubfeat(tuttid): report workspace UI mode assignment on fresh profile init (#Claude Code
  • 8d04a1b9 on GitHubtest(agent-gui): drop lazy BrowserNode renderError forwarding assertCursor Agent
  • 9433d564 on GitHubtest(agent-gui): wait for lazy BrowserNode before renderError assertCursor Agent
  • fe87e0f3 on GitHubfeat(browser-node): add optional renderError overlay seamCursor Agent
  • 73bcf2a2 on GitHubfeat(agent-gui): traycer-style sub-agent lane cards with real lifecycle stOpenAI Codex
  • 33715cf8 on GitHubfix(codex): forward child terminal markers and stop sub-agents on parent cOpenAI Codex
  • 8c092221 on GitHubfix(agent): classify stale codex app-server errorsOpenAI 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 window5,361
Merge commits removed−1,701
CI / dependency bots removed−0
Considered3,660

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 →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 tutti-os/tutti

Scan another repository

Try