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-source (Apache-2.0) orchestrator for Claude Code, Codex & 30+ coding agents. Plan, run and supervise agent teams from task to merged PR. Desktop (macOS, Windows, Linux) + iPhone & Android apps.

01Result

OrchestratorInc/agent-orchestrator ↗

OrchestratorInc/agent-orchestrator AI coding statistics: 36.9%

of 2,558 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
36.9% agent · top contributor 12.7%65 contributors
org-wide

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

945
agent commits
1,613
other considered commits
65
agent contributors
12.7%
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

944assisted
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
2026-0298.4%126
2026-0349.7%392
2026-0446.2%478
2026-0547%181
2026-0648.4%215
2026-0717.3%376
2026-0820.7%526
2026-0915.9%264

Peak month: 98.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic85133.3%
Cursor AgentAnysphere863.4%
GitHub CopilotGitHub150.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 29fda944 on GitHubfix(mobile): show a fallback instead of terminating when a screen throws (Claude Code
  • 380d87b8 on GitHubfix(mobile): ask the daemon about a session the board does not list (#5352Claude Code
  • 624cfcc3 on GitHubfix(tmux): classify an absent socket file as conclusive server absence (#4Claude Code
  • 9d2a9ef0 on GitHubfix(sidebar): sidebar ui revamp (#5447)Cursor Agent
  • d07b893b on GitHubfeat(browser): expand browser annotation workflows (#5396)Cursor Agent
  • b705fdef on GitHubfix(electron): return cancellation results for aborted browser-runtime comCursor Agent
  • d6fd5e5f on GitHubfeat: add standalone agent sessions (#4851)GitHub Copilot
  • 24e10191 on GitHubfeat(board): show PR progress for finished sessions (#4916)GitHub Copilot
  • da30da5a on GitHubfeat(review): configurable AO code review backend (V1) (#192) (#197)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 window2,766
Merge commits removed−200
CI / dependency bots removed−8
Considered2,558

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 →Go AI coding statisticsCompare evidence across Go 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 OrchestratorInc/agent-orchestrator

Scan another repository

Try