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

microsoft/agent-lightning ↗

microsoft/agent-lightning AI coding statistics: 3.5%

of 396 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.5% agent · top contributor 35.7%8 contributors
team

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

14
agent commits
382
other considered commits
8
agent contributors
35.7%
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

14assisted
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
2026-0220%5
2026-030%219
2026-040%98
2026-0520%15
2026-0620%15
2026-0720%5
2026-0816.7%30
2026-0911.1%9

Peak month: 20%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic92.3%
GitHub CopilotGitHub71.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1a2ef8a5 on GitHubfix(verl): make request aborts take effect on vLLM < 0.9 (pooling_output cClaude Code
  • 65df6ab5 on GitHubRewrite the skills README around how the skill works (#552)Claude Code
  • c632d8dd on GitHubRestore Python lint checks and extend them to the verl subtree (#553)Claude Code
  • 5518551e on GitHubClarify stable docs release verification (#563)GitHub Copilot
  • 4a610aee on GitHubfeat(async_swe_smith): online GRPO training example for SWE-smith (#34)GitHub Copilot
  • 9fcb436b on GitHubUpdate Search-R1 Llama 3 defaults (#32)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 window411
Merge commits removed−15
CI / dependency bots removed−0
Considered396

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
microsoft/agent-lightning
Default branch
main
Resolved HEAD
736dc6ab6867c3a720942c43c3d8d39bff299a9a ↗
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 position36th percentile

Midrank percentile; equal shares split the tied positions.

Repository
3.5%
Cohort median
6.3%
Share rank
157 / 247
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 247.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot 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 microsoft/agent-lightning

Scan another repository

Try