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.

Official Python SDK for the Agent2Agent (A2A) Protocol

01Result

a2aproject/a2a-python ↗

a2aproject/a2a-python AI coding statistics: 5.7%

of 298 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.7% agent · top contributor 35.3%9 contributors
org-wide

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

17
agent commits
281
other considered commits
9
agent contributors
35.3%
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

17assisted
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
2026-0214%43
2026-034.7%107
2026-042.4%82
2026-050%27
2026-060%4
2026-070%11
2026-0811.8%17
2026-0928.6%7

Peak month: 28.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Gemini CLIGoogle124%
GitHub CopilotGitHub31%
Cursor AgentAnysphere20.7%
Claude CodeAnthropic10.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 831fbed5 on GitHubtest: xfail legacy flaky test (#1028)Gemini CLI
  • ca7edc3b on GitHubfix: fix `athrow()` RuntimeError on streaming responses (#912)Gemini CLI
  • 4be2064b on GitHubrefactor(server)!: migrate from Application wrappers to Starlette route-baGemini CLI
  • 58c72c64 on GitHubfix: make event queue sink removal idempotent (#1134)GitHub Copilot
  • c24ae055 on GitHubfix(server): deliver push notifications across all owners (#1016)GitHub Copilot
  • 40613ed8 on GitHubchore: merge main into 1.0-dev (#658)GitHub Copilot
  • 57a9df3e on GitHubfix(server): validate push-notification URLs before dispatch (SSRF hardeniCursor Agent
  • 3eb88e22 on GitHubfix(server): validate push-notification URLs at config creation (#1173)Cursor Agent
  • 4554e2d6 on GitHubfix: replace deprecated FieldDescriptor.label with is_repeated in proto_utClaude Code

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 window339
Merge commits removed−16
CI / dependency bots removed−25
Considered298

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 a2aproject/a2a-python

Scan another repository

Try