Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Agent Package Manager

01Result

microsoft/apm ↗

microsoft/apm AI coding statistics: 78.4%

of 1,480 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
78.4% agent · top contributor 52.5%89 contributors
team

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

1,161
agent commits
319
other considered commits
89
agent contributors
52.5%
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

1077assisted
84autonomous

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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0226.6%79
2026-0360.1%326
2026-0478.2%225
2026-0592.5%226
2026-0698.1%210
2026-0780.7%197
2026-0888%75
2026-0990.1%142

Peak month: 98.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub114277.2%
Claude CodeAnthropic453%
Cursor AgentAnysphere30.2%
DevinCognition10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8fd10ac5 on GitHubchore: release v0.31.0 (#2989)GitHub Copilot
  • e08c2d55 on GitHubfix(cache): pin core.autocrlf=false on GitCache checkouts (#2982)GitHub Copilot
  • d478988e on GitHubtest(ci): repair stale daily release smoke fixtures (#2987)GitHub Copilot
  • c0cf0d27 on GitHubfix(utils): write project YAML with deterministic LF so apm.yml stops flipClaude Code
  • a8036285 on GitHubfix(deps): write synthetic package manifests with LF so content hashes matClaude Code
  • 8998d0ee on GitHubfix(init): reject empty/whitespace project names (#2200)Claude Code
  • a9625247 on GitHubfix(plugins): stop root-declared components copying the plugin into itselfCursor Agent
  • 41e3cdd3 on GitHubfeat(outdated): support monorepo tag nameing convention (#1504)Cursor Agent
  • 906d15ec on GitHubfeat(install): add GitLab marketplace host support (#1149)Cursor Agent
  • 7c7e0832 on GitHubfix: harden GitLab policy discovery (supersedes #2605, closes #2566) (#266Devin

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 window1,756
Merge commits removed−228
CI / dependency bots removed−48
Considered1,480

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 →Python AI coding statisticsCompare evidence across Python repositories →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/apm

Scan another repository

Try