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.

Experiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized model you own.

01Result

experientiallabs/experiential ↗

experientiallabs/experiential AI coding statistics: 55.1%

of 684 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
55.1% agent · top contributor 50.9%5 contributors
team

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

377
agent commits
307
other considered commits
5
agent contributors
50.9%
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

302assisted
75autonomous

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
2026-060%33
2026-0736.2%188
2026-0855.2%277
2026-0983.9%186

Peak month: 83.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic28141.1%
DevinCognition7911.5%
Cursor AgentAnysphere202.9%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8434a231 on GitHubgateway: a relearned refused payload survives the sweep of its stale queueClaude Code
  • c073063b on GitHubrelease: bump experiential to 0.7.80 (encrypted-reasoning memory scoped byClaude Code
  • 31d7d529 on GitHubgateway: scope the encrypted-reasoning memory by the admitted caller, not Claude Code
  • 25f006f7 on GitHubgateway: provider media handle carriers for image, document, and video inpDevin
  • b10fb2e8 on GitHubgateway: surface the rung's own rejection when narrowing fails and drop diDevin
  • fd353363 on GitHubAdd inline audio input on Chat, OpenAI-compatible, and Gemini wires (#731)Devin
  • c164547c on GitHubAdd identity-scoped, default-off gateway guardrails (#611)Cursor Agent
  • d045f09f on GitHubAccept OpenCode Chat Completions cache_control and drop it before routing Cursor Agent
  • 9082a402 on GitHubShow measured gateway latency on the README badge (#605)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 window684
Merge commits removed−0
CI / dependency bots removed−0
Considered684

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 →Python AI coding statisticsCompare evidence across Python 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 experientiallabs/experiential

Scan another repository

Try