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.

Algorithmic Trading in Python with Machine Learning

01Result

edtechre/pybroker ↗

edtechre/pybroker AI coding statistics: 33.9%

of 392 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

33.9% agent · top contributor 72.2%2 contributors

individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

133

agent commits

259

other considered commits

agent contributors

72.2%

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

133assisted

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

Peak month: 76.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	121	30.9%
Cursor Agent	Anysphere	12	3.1%

03Evidence

Inspect the matches

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

Matched commit samples

806b6538 on GitHubdeps: declare typing_extensions, and use what it makes available (#320)Claude Code
9caddb3f on GitHubdeps: floor optuna at 3.4, and unwind the re-seed's dead branch (#319)Claude Code
2523e05f on GitHubskill: always read the tag-to-tag diff, and trigger triage on any bump (#3Claude Code
4e386a66 on GitHubUpdate docs version to v2.0.0Cursor Agent
b1d0a919 on GitHubFix typecheck crash on NumPy 2.5 stubs after numba 0.67.Cursor Agent
2dc9e259 on GitHubRefresh notebooksCursor 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 window	440
Merge commits removed	−19
CI / dependency bots removed	−29
Considered	392

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 →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 edtechre/pybroker

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	3
2026-03	0%	8
2026-04	76.9%	13
2026-05	36.4%	11
2026-07	22.8%	101
2026-08	37.5%	256