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.

agent runtime security - zero trust, zero setup, zero latency agent sandboxing

nolabs-ai/nono ↗

nolabs-ai/nono AI coding statistics: 9.4%

of 1,217 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
9.4% agent · top contributor 26.1%31 contributors
org-wide

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

115
agent commits
1,102
other considered commits
31
agent contributors
26.1%
largest contributor

What shapes this result

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

Assisted or autonomous

115assisted
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
2026-022.6%116
2026-039.4%213
2026-049.9%324
2026-0514.5%227
2026-068.1%111
2026-075.7%105
2026-0812.7%71
2026-096%50

Peak month: 14.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic947.7%
Gemini CLIGoogle90.7%
Cursor AgentAnysphere80.7%
GitHub CopilotGitHub60.5%

Inspect the matches

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

Matched commit samples

  • d3c6f6b0 on GitHubfix(proxy): disable audit buffer for standalone \`nono proxy\` (#1766)Claude Code
  • 0c8a9c67 on GitHubfix(proxy): honour require_auth on the plain-HTTP forward path (#1673)Claude Code
  • cdf02fc9 on GitHubfix(why): fail on unresolvable network policy instead of degrading (#1554)Claude Code
  • ded24756 on GitHubUpdate README.md (#1223)Gemini CLI
  • 7d274cf7 on GitHubfeat: add $PACK_DIR support to session_hooks for store pack support (#1073Gemini CLI
  • 54c551eb on GitHubdocs(readme): update agent commands and enhance feature descriptions (#114Gemini CLI
  • 05727c51 on GitHubfix(proxy): read chunked HTTP request bodies on L7 forward path (#1687)Cursor Agent
  • ed91527c on GitHubfix(cli): honor inline custom credential routes in --config manifests (#17Cursor Agent
  • 3c79902e on GitHubfix(cli): warn when a draft profile cannot resolve its extends chain (#170Cursor Agent
  • ccdd26d3 on GitHubfix(why): tolerate volatile process-relative aliases in --self reload (#18GitHub Copilot
  • 1619275c on GitHubfeat: add profile-declared no_proxy bypass support (#1415)GitHub Copilot
  • 2663e990 on GitHubfeat(cli): add standalone `nono proxy` command (#1261)GitHub Copilot

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 window1,746
Merge commits removed−355
CI / dependency bots removed−174
Considered1,217

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 nolabs-ai/nono

Scan another repository