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

elizaOS/eliza ↗

elizaOS/eliza AI coding statistics: 35.1%

of 19,133 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
35.1% agent · top contributor 39.9%100 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

6,716
agent commits
12,417
other considered commits
100
agent contributors
39.9%
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

6713assisted
3autonomous

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
2026-0661.5%4196
2026-0750.4%5511
2026-0815.3%7888
2026-099.6%1538

Peak month: 61.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic661134.6%
Cursor AgentAnysphere960.5%
OpenAI CodexOpenAI120.1%
DevinCognition40%

03Evidence

Inspect the matches

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

Matched commit samples

  • d584c350 on GitHubtest(ui): give the client lanes a browser before the Story Gate timezone cClaude Code
  • 2d03d182 on GitHubtest(cloud): let the Worker placement test accept targeted placementClaude Code
  • f3a0173b on GitHubtest(scripts): build the receipt proof fixture with the continuity contracClaude Code
  • e908878f on GitHubfix(plugin-elizacloud): retry total voice catalog outages (#23406)Cursor Agent
  • 84bbd770 on GitHubfix(core): warm runtime probe cache off the boot critical pathCursor Agent
  • a30bac88 on GitHubfix(plugin-computeruse): reject PNG IHDR pixel bombs before inflate (#2230Cursor Agent
  • 160a095a on GitHubrelease: promote media and voice lifecycle recovery (#28104)OpenAI Codex
  • d8ea6152 on GitHubfix(app): retire unreachable Android OTA checkers (#24265)OpenAI Codex
  • 5ba741d7 on GitHubfix(app): preserve complete browser and OCR content (#24238)OpenAI Codex
  • b658d1e4 on GitHubfeat(desktop): cloud-only settings panel with hardened Cloud contracts (#2Devin
  • f3ffaee9 on GitHubfix(desktop): handle binary responses in Electrobun HTTP bridge to fix TTSDevin
  • f43d944a on GitHubchore(electrobun): add cloud login E2E benchmark script (#22950)Devin

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 window22,553
Merge commits removed−3,294
CI / dependency bots removed−126
Considered19,133

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
elizaOS/eliza
Default branch
develop
Resolved HEAD
ce97f6513629329649df92d82b02e81cc30d01e2 ↗
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.

CohortJS/TS · 376 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 194 of 570 ecosystem repositories excluded
Agent-commit share position88th percentile

Midrank percentile; equal shares split the tied positions.

Repository
35.1%
Cohort median
5.4%
Share rank
44 / 376
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 376.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Devin commitsBrowse repositories with detected Devin signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 elizaOS/eliza

Scan another repository

Try