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.

Optimize prompts, code, and more with AI-powered Reflective Optimization

01Result

gepa-ai/gepa ↗

gepa-ai/gepa AI coding statistics: 50.7%

of 205 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
50.7% agent · top contributor 70.2%11 contributors
team

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

104
agent commits
101
other considered commits
11
agent contributors
70.2%
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

92assisted
12autonomous

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
2026-010%1
2026-0242.4%66
2026-0370.8%24
2026-0444.4%45
2026-0570.6%17
2026-0666.7%6
2026-0751.5%33
2026-0840%10
2026-0966.7%3

Peak month: 70.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic8340.5%
GitHub CopilotGitHub167.8%
Cursor AgentAnysphere73.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7b924e2d on GitHubfix: skip seed valset evaluation when resuming from run_dir (#453)Claude Code
  • 65130973 on GitHubrefactor(oa): unify optimize_anything on a single GEPAResult return (#420)Claude Code
  • 874c7980 on GitHubdocs: show ComBEE's real rng default (None -> engine-bound RNG)Claude Code
  • e6fac476 on GitHubUpdate tests/proposer/test_signature_base.pyGitHub Copilot
  • 2968641b on GitHubFix Pyright type error: Add None checks for score comparisonGitHub Copilot
  • ba371250 on GitHubSet up PR 193 code state with Pyright errorGitHub Copilot
  • 15ee314f on GitHubFollow-up to #453: ValueError test + resume different seed is full-eval-anCursor Agent
  • 2075eaee on GitHubperf(combee): run single-job map calls as one batched wave (#436)Cursor Agent
  • b265bf9c on GitHubReduce redundant reflective trace context (#383)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 window243
Merge commits removed−37
CI / dependency bots removed−1
Considered205

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 →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 gepa-ai/gepa

Scan another repository

Try