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

comet-ml/opik ↗

comet-ml/opik AI coding statistics: 41.1%

of 2,549 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
41.1% agent · top contributor 13.3%47 contributors
org-wide

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

1,047
agent commits
1,502
other considered commits
47
agent contributors
13.3%
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

1042assisted
5autonomous

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
2026-0232.1%299
2026-0333.9%443
2026-0437.7%491
2026-0537.3%287
2026-0642.8%292
2026-0751.2%322
2026-0854.8%263
2026-0949.3%152

Peak month: 54.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic102540.2%
Cursor AgentAnysphere240.9%
GitHub CopilotGitHub10%

03Evidence

Inspect the matches

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

Matched commit samples

  • c610bf10 on GitHub[OPIK-8344] Emit opik_mcp_connected BI event on a new MCP connection (#828Claude Code
  • 91cd3f9e on GitHub[OPIK-8005] [FE] perf: virtualize the Playground output grid (#8312)Claude Code
  • b00e08ff on GitHub[OPIK-8334] [BE] fix: stop answering 500 for an OpenTelemetry request withClaude Code
  • 1e54d27e on GitHub[OPIK-4530] [BE] Add new permissions for dashboards and experiments (#5341Cursor Agent
  • a77a008b on GitHub[OPIK-4357] [FE] Implement view dashboards permission check (#5267)Cursor Agent
  • cbc23d0b on GitHub[OPIK-3522] Improve Playwright E2E test agent workflow (#5377)Cursor Agent
  • 21c43098 on GitHub[NA] [DOCS] Alert on python sdk docs deploy failure (#7545)GitHub Copilot

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 window2,657
Merge commits removed−0
CI / dependency bots removed−108
Considered2,549

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
comet-ml/opik
Default branch
main
Resolved HEAD
c800d72100c05fae3d06ae336c1409e9bdf8d359 ↗
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 position89th percentile

Midrank percentile; equal shares split the tied positions.

Repository
41.1%
Cohort median
6.3%
Share rank
28 / 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 →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 comet-ml/opik

Scan another repository

Try