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.

A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents

01Result

shepherd-agents/shepherd ↗

shepherd-agents/shepherd AI coding statistics: 82.5%

of 97 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
Too little recent activity to publish. Only 97 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.
82.5% agent · top contributor 83.8%5 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

80
agent commits
17
other considered commits
5
agent contributors
83.8%
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

80assisted
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
2026-06100%3
2026-0786.4%88
2026-080%5
2026-09100%1

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic7981.4%
OpenAI CodexOpenAI11%

03Evidence

Inspect the matches

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

Matched commit samples

  • 2d862488 on GitHubdocs(readme): point header logo at the clean PNG asset (#18)Claude Code
  • 254c9945 on GitHubdocs: 0.3.0 site sweep — new task syntax hero, apply verb, executed LandloClaude Code
  • a8196d4c on GitHubFinalize 0.3.0 release metadata: changelog, platform claim, grant-spellingClaude Code
  • d34d5ca3 on GitHubfeat: ship citation checking in Shepherd 0.3.1 (#55)OpenAI Codex

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 window126
Merge commits removed−29
CI / dependency bots removed−0
Considered97

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 shepherd-agents/shepherd

Scan another repository

Try