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.

AI Observability & Evaluation

01Result

Arize-ai/phoenix ↗

Arize-ai/phoenix AI coding statistics: 12.4%

of 2,696 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

12.4% agent · top contributor 41.3%31 contributors

org-wide

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

334

agent commits

2,362

other considered commits

agent contributors

41.3%

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

327assisted

7autonomous

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

Peak month: 22.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	312	11.6%
Cursor Agent	Anysphere	21	0.8%
GitHub Copilot	GitHub	6	0.2%
OpenAI Codex	OpenAI	1	0%

03Evidence

Inspect the matches

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

Matched commit samples

06a21cd0 on GitHubfix(agents): retain partial output on interrupted turn spans (#15457)Claude Code
856a9b6e on GitHubtest(datasets): cover cross-dataset split example countsClaude Code
e60697fe on GitHubfeat(server): add GET /datasets/{dataset_identifier}/splitsClaude Code
75fd29c3 on GitHubfeat(mcp): include the Phoenix docs MCP in the Cursor pluginCursor Agent
570d280f on GitHubfeat(mcp): add a Cursor plugin for the remote MCP server and public skillsCursor Agent
58b70172 on GitHubfeat(app): add Z.ai as a built-in GLM model provider (#15857)Cursor Agent
7efa7b21 on GitHubfeat(evals): add retrieval relevance evaluator (#14766)GitHub Copilot
1aa1a845 on GitHubfeat(evals): add hallucination evaluator (#14708)GitHub Copilot
e93efb99 on GitHubFix prompt description tab sidebar scrolling (#14723)GitHub Copilot
516d1eb6 on GitHubCodex changes (#11356)OpenAI Codex

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 window	2,854
Merge commits removed	−30
CI / dependency bots removed	−128
Considered	2,696

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 Arize-ai/phoenix

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	10.2%	558
2026-03	10.7%	307
2026-04	5%	261
2026-05	20.2%	267
2026-06	13.9%	244
2026-07	11.8%	441
2026-08	10.7%	402
2026-09	22.2%	216