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.

An open-source, AI-integrated, cross-platform terminal for seamless workflows

01Result

wavetermdev/waveterm ↗

wavetermdev/waveterm AI coding statistics: 28.3%

of 184 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
28.3% agent · top contributor 88.5%6 contributors
individual

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

52
agent commits
132
other considered commits
6
agent contributors
88.5%
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

52assisted
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
2026-0220.3%69
2026-0338.9%95
2026-046.3%16
2026-050%2
2026-070%2

Peak month: 38.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub4725.5%
Claude CodeAnthropic52.7%

03Evidence

Inspect the matches

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

Matched commit samples

  • 889e6287 on GitHubShow Claude icon in terminal header while Claude Code is active (#3046)GitHub Copilot
  • 24de0c1b on GitHubDeprecate the legacy `waveai` block UI and add a preview for its replacemeGitHub Copilot
  • 4a28c4b1 on GitHubDiffing RenderedElem trees to produce VDomPatch (#3104)GitHub Copilot
  • 1fe0fa23 on GitHubfix: trim trailing whitespace from terminal clipboard copies (#3167)Claude Code
  • 57e4e27a on GitHubfeat: add opt-in split buttons to block headers (#3159)Claude Code
  • 86ed5e1f on GitHubdocs: add Traditional Chinese (zh-TW) README translation (#3157)Claude Code

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 window283
Merge commits removed−0
CI / dependency bots removed−99
Considered184

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 →Go AI coding statisticsCompare evidence across Go 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 wavetermdev/waveterm

Scan another repository

Try