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.

Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.

Atmosphere/atmosphere ↗

Atmosphere/atmosphere AI coding statistics: 0%

of 2,363 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

No signed agent commits found

No agent signatures were found in the last 2,363 considered commits. That is a real result, not a failure to measure.

It does not mean no AI was used here. A developer can use an agent and commit by hand without leaving a detectable git signature.

1
agent commits
2,362
other considered commits
1
agent contributors
100%
largest contributor

What shapes this result

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

No agent signatures were detected, so there are no agent, mode, or timing drivers to break down.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic10%

Inspect the matches

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

Matched commit samples

  • 22e50d8f on GitHubtest(e2e): implement 5-gap E2E test expansion proposal CLI runtime tests, Claude Code

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 window2,443
Merge commits removed−26
CI / dependency bots removed−54
Considered2,363

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 Atmosphere/atmosphere

Scan another repository