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.

Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Docker deployment.

01Result

bethington/ghidra-mcp ↗

bethington/ghidra-mcp AI coding statistics: 67.8%

of 818 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
67.8% agent · top contributor 84.7%12 contributors
individual

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

555
agent commits
263
other considered commits
12
agent contributors
84.7%
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

554assisted
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
2026-0240%70
2026-0321%105
2026-0473.7%198
2026-0590.5%84
2026-0657.8%90
2026-0780.7%57
2026-0886.5%208
2026-0983.3%6

Peak month: 90.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic55167.4%
GitHub CopilotGitHub40.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • e78351e2 on GitHubci(dependabot): group codeql-action bumps, drop the removed fun-doc ecosysClaude Code
  • 084a057a on GitHubdocs(params): describe every advertised parameter (294 to 0) (#454)Claude Code
  • 6dfb31a3 on GitHubci: pay off the coverage debt and raise the floor to 67 (#453)Claude Code
  • a36b86bf on GitHubPotential fix for pull request finding 'CodeQL / Information exposure throGitHub Copilot
  • 1a101754 on GitHubPotential fix for pull request finding 'CodeQL / Information exposure throGitHub Copilot
  • a8948bf5 on GitHubPotential fix for pull request finding 'CodeQL / Information exposure throGitHub 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 window988
Merge commits removed−79
CI / dependency bots removed−91
Considered818

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 →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 bethington/ghidra-mcp

Scan another repository

Try