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.

Open-Source Personal Cloud OS for Always-On Agents

01Result

beclab/Olares ↗

beclab/Olares AI coding statistics: 20%

of 1,332 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
20% agent · top contributor 47.6%15 contributors
org-wide

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

267
agent commits
1,065
other considered commits
15
agent contributors
47.6%
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

267assisted
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
2026-020%65
2026-030%155
2026-040.7%146
2026-0516.8%173
2026-0630.5%282
2026-0719.4%227
2026-0836.2%210
2026-0941.9%74

Peak month: 41.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere26319.7%
Claude CodeAnthropic50.4%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 787342b4 on GitHubsystem-frontend: update image to v1.11.53 (#4147)Cursor Agent
  • 4c4e4396 on GitHubdocs(cli): correct the market lifecycle references against a test runCursor Agent
  • c9e3b5be on GitHubfix(cli): report what market and chart verbs actually didCursor Agent
  • 5daa5051 on GitHubfeat(mesh) — Linkerd mesh for Shared in-cluster traffic (#3785)Claude Code
  • 1b6d46e7 on GitHubdocs: fix get-started snippet links and restyle GPU passthrough tutorial (Claude Code
  • 7969b684 on GitHubdocs: deduplicate H1 titles and batch add Chinese translations (#3455)Claude Code
  • 2fc1b59c on GitHubdaemon: prevent ICMP port-unreachable responses (#2960)GitHub Copilot

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 window1,380
Merge commits removed−40
CI / dependency bots removed−8
Considered1,332

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 →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 beclab/Olares

Scan another repository

Try