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.

A HTTP credential proxy and vault for AI agents like Claude Code, OpenClaw, Hermes, custom agents + harnesses, and more.

01Result

Infisical/agent-vault ↗

Infisical/agent-vault AI coding statistics: 63.2%

of 209 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
63.2% agent · top contributor 68.2%8 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

132
agent commits
77
other considered commits
8
agent contributors
68.2%
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

127assisted
5autonomous

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
2026-0394.4%18
2026-0497.1%105
2026-0517.1%41
2026-0616.2%37
2026-070%1
2026-080%2
2026-090%5

Peak month: 97.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic12760.8%
DevinCognition41.9%
Cursor AgentAnysphere10.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • fb2bb814 on GitHubdocs(openclaw): add VPS guide callout to quickstart (#251)Claude Code
  • e3de9e0e on GitHubdocs(openclawvpsguide): built out the doc for the OpenClaw VPS Guide. (#2Claude Code
  • d3b08a73 on GitHubfeat: external credential stores (Infisical integration) (#206)Claude Code
  • 3bd0c1e9 on GitHubfeat: add Pi, Devin, Windsurf, Cline, and Roo Code to knownAgents (#295)Devin
  • fc0443d9 on GitHubfeat: resolve actor names in request log details (#292)Devin
  • f07170af on GitHubdocs: add enterprise CTA banners to PostgreSQL self-hosting page (#288)Devin
  • b8cb82e3 on GitHubagents: remove invite ceremony, add direct create + rotate (#176)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 window328
Merge commits removed−1
CI / dependency bots removed−118
Considered209

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 →Devin commitsBrowse repositories with detected Devin 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 Infisical/agent-vault

Scan another repository

Try