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.

Infrastructure for continually self‑improving agents

01Result

Human-Agent-Society/reef ↗

Human-Agent-Society/reef AI coding statistics: 17.1%

of 281 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
17.1% agent · top contributor 52.1%10 contributors
team

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

48
agent commits
233
other considered commits
10
agent contributors
52.1%
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

48assisted
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
2026-0813.3%30
2026-0917.5%251

Peak month: 17.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic4516%
GitHub CopilotGitHub31.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 58765b7f on GitHubfeat: let Reef own inference and training coordination (#432)Claude Code
  • 99132828 on GitHubrefactor(tinker): fix dependency direction, one loss-family table, custom-Claude Code
  • ad08ac47 on GitHubfeat(deploy): startup settings report, strict null and repeated YAML keys Claude Code
  • 73831f2b on GitHubStabilize flaky CI test in commit-log harness growth path (Python 3.10) (#GitHub Copilot
  • 63aa4ea8 on GitHubdocs: install ollama from the tarball in the Colab setup cell (#126)GitHub Copilot
  • b558d972 on GitHubdocs: add the standard header README to each weight recipe package (#119)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 window290
Merge commits removed−0
CI / dependency bots removed−9
Considered281

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 →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 Human-Agent-Society/reef

Scan another repository

Try