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.

Multi-platform SDK for integrating GitHub Copilot Agent into apps and services

01Result

github/copilot-sdk ↗

github/copilot-sdk AI coding statistics: 65%

of 823 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

65% agent · top contributor 24.1%83 contributors

org-wide

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

535

agent commits

288

other considered commits

agent contributors

24.1%

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

446assisted

89autonomous

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

Peak month: 73.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	534	64.9%
Claude Code	Anthropic	2	0.2%
Cursor Agent	Anysphere	1	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

e9df3938 on GitHubPublish .NET SDK to the internal feed (#2614)GitHub Copilot
9553d522 on GitHubIsolate hostless runtime cache (#2659)GitHub Copilot
a675b555 on GitHubStabilize C# rewind E2E initialization (#2661)GitHub Copilot
273c425a on GitHubAllow custom npm registry URL for downloading Copilot from dotnet SDK (#46Claude Code
fb767b50 on GitHubRemove typing-extensions from dev dependencies (#147)Claude Code
76a9f180 on GitHubtest(java): re-enable ModeHandlers exit_plan_mode E2E assertions (#2032)Cursor Agent

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	1,033
Merge commits removed	−0
CI / dependency bots removed	−210
Considered	823

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 →Java AI coding statisticsCompare evidence across Java 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 github/copilot-sdk

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	38.2%	89
2026-03	59.8%	107
2026-04	58.7%	63
2026-05	73.2%	183
2026-06	72.5%	109
2026-07	68.7%	115
2026-08	66.2%	71
2026-09	70.9%	86