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.

Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions

01Result

awslabs/cli-agent-orchestrator ↗

awslabs/cli-agent-orchestrator AI coding statistics: 28.4%

of 342 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
28.4% agent · top contributor 37.1%17 contributors
org-wide

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

97
agent commits
245
other considered commits
17
agent contributors
37.1%
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

97assisted
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
2026-0238.5%13
2026-0352.4%21
2026-0457.1%42
2026-0535.7%28
2026-0624.3%37
2026-0723%100
2026-0820%70
2026-093.2%31

Peak month: 57.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic7822.8%
GitHub CopilotGitHub247%
Cursor AgentAnysphere10.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • a5ccbe26 on GitHubfix(release): stop publishing a macOS x86_64 wheel that cannot install (#7Claude Code
  • 2a9d92a0 on GitHubfix(release): repair the per-platform wheel matrix on its first real run (Claude Code
  • 8852d26a on GitHubfeat(workflow): frozen execution manifest, plan approval, and frozen run mClaude Code
  • ce18db23 on GitHubdocs: clarify PTY WebSocket authorization (#749)GitHub Copilot
  • 74a8db43 on GitHubfeat(examples): add AI-DLC portfolio orchestration example (#521)GitHub Copilot
  • d77075fd on GitHubfeat(workflow): script-tier run surface + author shim — U5+U6 (#312) (#399GitHub Copilot
  • 93336acd on GitHubfeat: Official devcontainer feature for CAO (#260)Cursor 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 window394
Merge commits removed−0
CI / dependency bots removed−52
Considered342

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 →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 awslabs/cli-agent-orchestrator

Scan another repository

Try