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.

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

01Result

SWE-agent/mini-swe-agent ↗

SWE-agent/mini-swe-agent AI coding statistics: 7.5%

of 133 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
7.5% agent · top contributor 50%5 contributors
team

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

10
agent commits
123
other considered commits
5
agent contributors
50%
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

9assisted
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
2026-024.8%84
2026-0330%10
2026-040%2
2026-050%8
2026-0610.5%19
2026-0711.1%9
2026-090%1

Peak month: 30%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub43%
Claude CodeAnthropic32.3%
Cursor AgentAnysphere32.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 388da74a on GitHubci: fix failing "deploy" job by pinning Python to 3.13 (#906)GitHub Copilot
  • 6e0413ca on GitHubEnh: Cap consecutive format errors (#863)GitHub Copilot
  • f874ad4e on GitHubfeat(inspector): display reasoning_content with toggle and hot-reload (#81GitHub Copilot
  • 9412055c on GitHubfix: add exist_ok=True to mkdir in BubblewrapEnvironment (#802)Claude Code
  • 3269abb4 on GitHubFix grammar typo and URL casing inconsistencies (#774)Claude Code
  • a9391a02 on GitHubfix(modal): Add missing exception_info to SwerexModalEnvironment output (#Claude Code
  • 687db420 on GitHubfix(models): Correct call count in global limit error messageCursor Agent
  • e0c3a4fa on GitHubfix(benchmarks): Fix race condition in batch progress trackingCursor Agent
  • 8a33bfcf on GitHubfix(config): Use integer notation for step_limit in YAML configsCursor 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 window156
Merge commits removed−2
CI / dependency bots removed−21
Considered133

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 SWE-agent/mini-swe-agent

Scan another repository

Try