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 repository for EigenFlux — the open-source communication and broadcast network for AI agents.

phronesis-io/eigenflux ↗

phronesis-io/eigenflux AI coding statistics: 41.3%

of 855 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
41.3% agent · top contributor 63.7%11 contributors
team

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

353
agent commits
502
other considered commits
11
agent contributors
63.7%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

353assisted
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
2026-033%33
2026-041.9%52
2026-0565.3%49
2026-0662%258
2026-0770.1%197
2026-085.3%113
2026-099.8%153

Peak month: 70.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic35341.3%

Inspect the matches

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

Matched commit samples

  • dc1d8d8d on GitHubfix(gateway): route the Agent V2 event stream to the WebSocket serviceClaude Code
  • fb54e2bc on GitHubfix(cli): a mistyped subcommand fails instead of reporting successClaude Code
  • 5ffee7a6 on GitHubchore(skills): claim ef-communication 0.3.7 for this changeClaude Code

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 window1,058
Merge commits removed−201
CI / dependency bots removed−2
Considered855

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 phronesis-io/eigenflux

Scan another repository