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

mastra-ai/mastra ↗

mastra-ai/mastra AI coding statistics: 14.4%

of 5,422 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
14.4% agent · top contributor 34.5%125 contributors
org-wide

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

780
agent commits
4,642
other considered commits
125
agent contributors
34.5%
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

509assisted
271autonomous

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
2026-010%2
2026-0228.7%540
2026-0312.9%669
2026-0417.5%576
2026-0524%646
2026-0614.8%741
2026-078%934
2026-089.2%876
2026-093.9%438

Peak month: 28.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic4728.7%
DevinCognition2815.2%
Cursor AgentAnysphere220.4%
GitHub CopilotGitHub120.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 2810b716 on GitHubfix(observability): forward exact OpenRouter costs to Langfuse (#20336)Claude Code
  • cf28f10d on GitHubfix(playground): collect auth headers on the blocked screen (#21214)Claude Code
  • cf9cd796 on GitHubrefactor(core): fold text and reasoning spans through one shared unit (#23Claude Code
  • b0f9b0c0 on GitHubdocs: revert documentation changes from #23077 (#24031)Devin
  • 8365094a on GitHubdocs: move client-js agent controller events into a Client SDK reference pDevin
  • 74f60deb on GitHubdocs: cover the client-js path in agent controller "Connect a UI" (#22788)Devin
  • 164e197a on GitHubfix: bump vulnerable dependencies to patched releases (#24027)Cursor Agent
  • 53d72502 on GitHubfix: bump fastify/fast-uri and related High vulns (SEC-170/171) (#23665)Cursor Agent
  • 571d66f6 on GitHubfix(evals): honor empty trajectories and nested blacklist failures (#23505Cursor Agent
  • b390381c on GitHubfix(e2b, blaxel): S3 mount race condition and partial credential validatioGitHub Copilot
  • 975c59ae on GitHubfeat(core): make agentic-loop serialization-safe on the evented engine (#1GitHub Copilot
  • 65f255a3 on GitHubfix(core): guard CacheKeyGenerator against empty/undefined reasoning detaiGitHub 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 window6,963
Merge commits removed−0
CI / dependency bots removed−1,541
Considered5,422

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
mastra-ai/mastra
Default branch
main
Resolved HEAD
aa38e6f424a0eae0e43a5c2ae0b387e404f5e6a6 ↗
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 position71st percentile

Midrank percentile; equal shares split the tied positions.

Repository
14.4%
Cohort median
5.4%
Share rank
111 / 376
0th50th100th

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

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 →Devin commitsBrowse repositories with detected Devin 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 mastra-ai/mastra

Scan another repository

Try