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.

Open-source, local-first apps.

EpicenterHQ/epicenter ↗

EpicenterHQ/epicenter AI coding statistics: 0.6%

of 10,441 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
0.6% agent · top contributor 98.3%2 contributors
individual

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

58
agent commits
10,383
other considered commits
2
agent contributors
98.3%
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

58assisted
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
2026-010%8
2026-020%775
2026-030.5%1563
2026-040%1563
2026-052.7%1841
2026-060%2001
2026-070%1421
2026-080%938
2026-090%331

Peak month: 2.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic580.6%

Inspect the matches

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

Matched commit samples

  • 8c63535b on GitHubdocs(specs): sweep auth spec to unified Cloud App vocabularyClaude Code
  • 4413a266 on GitHubrefactor(tab-manager): split device-identity helpers into device.tsClaude Code
  • 1a77cfa8 on GitHubrefactor(tab-manager): delegate requireWorkspace to the framework's methodClaude 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 window12,155
Merge commits removed−1,340
CI / dependency bots removed−374
Considered10,441

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 EpicenterHQ/epicenter

Scan another repository