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.

The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.

01Result

boxlite-ai/boxlite ↗

boxlite-ai/boxlite AI coding statistics: 18.8%

of 696 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
18.8% agent · top contributor 45%16 contributors
org-wide

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

131
agent commits
565
other considered commits
16
agent contributors
45%
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

131assisted
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
2026-0219.2%104
2026-034.3%70
2026-045%20
2026-0516.7%90
2026-0629.6%125
2026-078.5%71
2026-0821.4%187
2026-0931%29

Peak month: 31%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic11216.1%
GitHub CopilotGitHub131.9%
Cursor AgentAnysphere111.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1f68ee36 on GitHubfeat(net): cap per-box network bandwidth (#1435)Claude Code
  • 783609f2 on GitHubfix(api): wake a stopped autoResume box when a tunnel is opened, instead oClaude Code
  • fb41cf86 on GitHubtest(jailer): pair host-grant test with network.mode=disabled (#1457)Claude Code
  • 5c0b1565 on GitHubtest(e2e): bring Tokyo e2e suite to green (split from #724) (#810)GitHub Copilot
  • cf69a05f on GitHubrefactor(infra-local): simplify + unify into one Python `compose` package GitHub Copilot
  • ba7458d0 on GitHubfix(sdk): make boxlite_options_add_port carry the full PortSpec (#741)GitHub Copilot
  • 791ae384 on GitHubfix(runtime): resync guest clock after host sleep and quiesce (#899)Cursor Agent
  • cc236c41 on GitHubChore/cli ci test (#221)Cursor Agent
  • 72a6935b on GitHubfeat(sdk): expose resize_tty in Python SDK and add AI agent guide (#220)Cursor Agent

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 window726
Merge commits removed−0
CI / dependency bots removed−30
Considered696

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 boxlite-ai/boxlite

Scan another repository

Try