Dataset: 2026-09-18-v3.0
Ruleset: b2e8889c66f7
Scanned: 2026-09-16
Window: February–September 15, 2026

Local to this browser

01Result

PostHog/posthog ↗

PostHog/posthog AI coding statistics: 16.7%

of 24,854 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

16.7% agent · top contributor 8.3%159 contributors

org-wide

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

4,155

agent commits

20,699

other considered commits

159

agent contributors

8.3%

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

4107assisted

48autonomous

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
Month	Agent share	Considered commits
2026-02	14.2%	2030
2026-03	16.3%	2401
2026-04	15.5%	2594
2026-05	15.1%	2087
2026-06	16.5%	4252
2026-07	14.9%	4718
2026-08	17.9%	4383
2026-09	23.8%	2389

Peak month: 23.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	3969	16%
Cursor Agent	Anysphere	121	0.5%
GitHub Copilot	GitHub	92	0.4%
OpenAI Codex	OpenAI	2	0%

03Evidence

Inspect the matches

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

Matched commit samples

04dabfcc on GitHubfeat(replay-vision): have scanners judge how notable a session is (#99483)Claude Code
bda79c29 on GitHubfix(desktop): improve self-driving report dialogs (#100815)Claude Code
d89bcde7 on GitHubfix(lemon-ui): make modals scrollable on mobile Safari (#78305)Claude Code
38ae7b0e on GitHubfix(mcp): advertise exec tool annotations on tools/list (#101294)Cursor Agent
482536bb on GitHubchore(conversations): support reply eval harness (#100918)Cursor Agent
06e90ce8 on GitHubfeat(business knowledge): search pagination filters (#100822)Cursor Agent
7cba4577 on GitHubfeat(reviewhog): put issue description first in finding comments (#93907)GitHub Copilot
e376772c on GitHubfix(cohorts): stop server-side cursor scan in dependency cache warm (#7597GitHub Copilot
562c9a85 on GitHubfix(hogql): drop the unbounded count from property autocomplete (#85984)GitHub Copilot
36b49cb6 on GitHubchore(devex): stop typegen from dirtying untouched logic files (#100420)OpenAI Codex
ec7e37fa on GitHubfix(insights): default stickiness sql expression to person_id (#53854)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 window	27,160
Merge commits removed	−0
CI / dependency bots removed	−2,306
Considered	24,854

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: PostHog/posthog
Default branch: master
Resolved HEAD: 3d8b7f49ee24722de4988b114d59cd17991926e6 ↗
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.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded

Agent-commit share position73rd percentile

Midrank percentile; equal shares split the tied positions.

Repository: 16.7%
Cohort median: 6.3%
Share rank: 67 / 247

0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 247.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 PostHog/posthog

Scan another repository

Try