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.

The Unofficial and Awesome Home Assistant MCP Server

01Result

homeassistant-ai/ha-mcp ↗

homeassistant-ai/ha-mcp AI coding statistics: 51.6%

of 973 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
51.6% agent · top contributor 62.2%36 contributors
team

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

502
agent commits
471
other considered commits
36
agent contributors
62.2%
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

488assisted
14autonomous

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
2026-010%1
2026-0256.8%74
2026-0353.8%80
2026-0430.7%101
2026-0544.5%236
2026-0661.4%101
2026-0765.9%211
2026-0848.7%117
2026-0944.2%52

Peak month: 65.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic49550.9%
Gemini CLIGoogle90.9%
GitHub CopilotGitHub60.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 5d98acb3 on GitHubfix: point unknown tool arguments at the intended parameter (#2465)Claude Code
  • fc7d03b4 on GitHubdocs: restore scope anti-patterns and move general code conventions into AClaude Code
  • f5bfd69e on GitHubfeat: add check_updates action to reload the app store (#2460)Claude Code
  • 76a2a7ed on GitHubdocs: surface tool-discovery / categorized search (#1123)Gemini CLI
  • dda6031f on GitHubAdded feature flags for gated features to App config. (#1030)Gemini CLI
  • 156492d6 on GitHubfeat: Add generic add-on API proxy tool (ha_call_addon_api) (#641)Gemini CLI
  • af656b5f on GitHubfix: recover legacy embedded server upgrades (#1838)GitHub Copilot
  • dda6031f on GitHubAdded feature flags for gated features to App config. (#1030)GitHub Copilot
  • a6ff2fe8 on GitHubfix(site): replace placeholder logo SVGs with real brand icons (#910)GitHub 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 window2,035
Merge commits removed−3
CI / dependency bots removed−1,059
Considered973

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 homeassistant-ai/ha-mcp

Scan another repository

Try