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.

AI You Control: Choose your models. Own your data. Eliminate vendor lock-in.

01Result

thunderbird/thunderbolt ↗

thunderbird/thunderbolt AI coding statistics: 10.5%

of 608 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
10.5% agent · top contributor 29.7%10 contributors
org-wide

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

64
agent commits
544
other considered commits
10
agent contributors
29.7%
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

61assisted
3autonomous

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
2026-021.4%74
2026-0323.5%102
2026-0416.1%124
2026-051.3%77
2026-064.9%61
2026-0714.3%84
2026-086.3%48
2026-090%38

Peak month: 23.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic508.2%
Cursor AgentAnysphere152.5%
OpenAI CodexOpenAI20.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 581ff71d on GitHubfix(dev): add SELinux :Z labels to postgres/powersync bind mounts (#1084)Claude Code
  • ec8d7b79 on GitHubfix(THU-539): skip pulumi destroy when stack is already gone (#983)Claude Code
  • 29dc18e5 on GitHubfeat(skills): expose ACP agent commands in the chat slash menu (#964)Claude Code
  • 510fbd3e on GitHubTHU-810: Derive unit defaults from locale and clean up the units data fileCursor Agent
  • cc5f6712 on GitHubci: allow thunderbolt-automation-agent bot in deep review (#1182)Cursor Agent
  • 7840df67 on GitHubfeat(design): redesign part 6 (#1145)Cursor Agent
  • 1689e623 on GitHubfeat(THU-748): enforce web tool turn budgets (#1175)OpenAI Codex
  • 6e6be924 on GitHubfix(THU-694): web-CLI bridge resilience — survive relay restarts without aOpenAI Codex

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 window634
Merge commits removed−6
CI / dependency bots removed−20
Considered608

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 thunderbird/thunderbolt

Scan another repository

Try