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.

ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.

stacklok/toolhive ↗

stacklok/toolhive AI coding statistics: 55.7%

of 1,468 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
55.7% agent · top contributor 24.4%36 contributors
org-wide

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

818
agent commits
650
other considered commits
36
agent contributors
24.4%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

805assisted
13autonomous

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
2026-0241.3%201
2026-0360.3%257
2026-0455.7%327
2026-0548.7%117
2026-0685%153
2026-0764.7%184
2026-0841.8%146
2026-0937.3%83

Peak month: 85%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic79554.2%
Cursor AgentAnysphere201.4%
GitHub CopilotGitHub40.3%

Inspect the matches

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

Matched commit samples

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 window1,821
Merge commits removed−0
CI / dependency bots removed−353
Considered1,468

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 stacklok/toolhive

Scan another repository