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.

F´ - A flight software and embedded systems framework

01Result

nasa/fprime ↗

nasa/fprime AI coding statistics: 49%

of 584 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
49% agent · top contributor 79.4%22 contributors
team

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

286
agent commits
298
other considered commits
22
agent contributors
79.4%
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

286assisted
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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-022.6%38
2026-033.2%62
2026-0417.6%51
2026-0547.8%46
2026-0648.5%68
2026-0771.1%121
2026-0865%137
2026-0972.1%61

Peak month: 72.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
DevinCognition26244.9%
Claude CodeAnthropic183.1%
GitHub CopilotGitHub101.7%
Cursor AgentAnysphere20.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 198092c8 on GitHubrequirements: add fprime-yamcs 0.2.1 and its dependencies; bump fprime-gdsDevin
  • f19f80fb on GitHubSvc/CmdDispatcher: make dropped-command counter atomic (#5962)Devin
  • 011ad5be on GitHubSvc/Version: emit custom version events regardless of verbosity; count popDevin
  • fd1c5517 on GitHubAdd fail-closed sandbox confinement to Svc::FileManager command paths (#58Claude Code
  • 3c4eb901 on GitHubReport overlong hash-file names instead of asserting in Utils::CRCChecker Claude Code
  • ebd8e418 on GitHubfix(CdhCore): stabilize flaky test_telemetry_update (#5765)Claude Code
  • d75b4dd8 on GitHubRevise cross-compilation tutorial for clarity (#5727)GitHub Copilot
  • 793cef2c on GitHubAdd ISR-based device driver pattern documentation (#4681)GitHub Copilot
  • 5a720f1d on GitHubMigrate agent skills to the standard .github/skills/<name>/SKILL.md layoutGitHub Copilot
  • fb8f2074 on GitHubSoak Testing Workflow Updates (#5302)Cursor Agent
  • 2ed40ebd on GitHubWorkflows for RPI 5 Soak Testing LedBlinker (#5265)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 window594
Merge commits removed−0
CI / dependency bots removed−10
Considered584

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 →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 nasa/fprime

Scan another repository

Try