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.

Apache Thrift

01Result

apache/thrift ↗

apache/thrift AI coding statistics: 47.7%

of 654 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
47.7% agent · top contributor 89.4%15 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

312
agent commits
342
other considered commits
15
agent contributors
89.4%
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

311assisted
1autonomous

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
2026-028.3%24
2026-038.8%34
2026-0425.9%85
2026-0541.5%135
2026-0673.2%56
2026-0743.6%101
2026-0816.9%65
2026-0986.4%154

Peak month: 86.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic30546.6%
GitHub CopilotGitHub60.9%
Gemini CLIGoogle20.3%
OpenAI CodexOpenAI20.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1311cf36 on GitHubCap the capacity reserved for a container's declared element countClaude Code
  • 843d81ca on GitHubTHRIFT-6274: Reject AI session and conversation links in pull requests CliClaude Code
  • 44130f0d on GitHubCap the capacity reserved for a container's declared element countClaude Code
  • e455f325 on GitHubTHRIFT-6069: python: avoid utf8 copy during fastbinary string encode (#359GitHub Copilot
  • ab9b2a96 on GitHubPreserve private_optional field orderGitHub Copilot
  • 83dcfe24 on GitHubTHRIFT-5951: Improve PHP library unit test coverage (#3432)GitHub Copilot
  • d1138eec on GitHubTHRIFT-6203: Replace deprecated url.parse and fs.exists in Node.js web_serGemini CLI
  • 9f11dfb1 on GitHubTHRIFT-5224: Replace the deprecated Buffer() constructor in the Node.js liGemini CLI
  • eee7d03a on GitHubTHRIFT-3165: Set C++ default TLS protocol floorOpenAI Codex
  • 11d82075 on GitHubTHRIFT-6070: Publish Python wheel distributions to PyPIOpenAI Codex

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 window723
Merge commits removed−4
CI / dependency bots removed−65
Considered654

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Gemini CLI commitsBrowse repositories with detected Gemini CLI signatures →C++ AI coding statisticsCompare evidence across C++ 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 apache/thrift

Scan another repository

Try