Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

permissionlesstech/bitchat ↗

permissionlesstech/bitchat AI coding statistics: 62.5%

of 248 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
62.5% agent · top contributor 62.6%6 contributors
team

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

155
agent commits
93
other considered commits
6
agent contributors
62.6%
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

155assisted
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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0216.7%6
2026-030%16
2026-040%15
2026-050%10
2026-0686.5%52
2026-0770.1%127
2026-0890.9%22

Peak month: 90.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic14859.7%
Cursor AgentAnysphere93.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 9b84b361 on GitHubLocalize the last hardcoded UI strings; wire up two dead translations (#16Claude Code
  • 5c4b814c on GitHubLocalize CommandProcessor: all 48 command strings, 30 locales (#1657)Claude Code
  • eca14719 on GitHubAdd 26 code-referenced keys to the catalog + a test that closes the gap (#Claude Code
  • 1f59e814 on GitHubKeyboard navigation for @-mention suggestions (#1542)Cursor Agent
  • 01523445 on GitHubfeat: verification seal on private message sender rows (#1573)Cursor Agent
  • 681c1800 on GitHubfeat: share location channel invites via the system share sheet (#1513)Cursor 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 window257
Merge commits removed−9
CI / dependency bots removed−0
Considered248

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

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
permissionlesstech/bitchat
Default branch
main
Resolved HEAD
9b84b361225facd8e623f25d76f889d3dc54a879 ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortSwift · 14 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 9 of 23 ecosystem repositories excluded
Agent-commit share position96th percentile

Midrank percentile; equal shares split the tied positions.

Repository
62.5%
Cohort median
2.3%
Share rank
1 / 14
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 14.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →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 permissionlesstech/bitchat

Scan another repository

Try