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.

E2B Desktop Sandbox for LLMs. E2B Sandbox with desktop graphical environment that you can connect to any LLM for secure computer use.

01Result

e2b-dev/desktop ↗

e2b-dev/desktop AI coding statistics: 76%

of 25 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

Too little recent activity to publish. Only 25 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.

76% agent · top contributor 63.2%3 contributors

individual

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

agent commits

other considered commits

agent contributors

63.2%

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

12assisted

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	12	48%
Devin	Cognition	6	24%
GitHub Copilot	GitHub	1	4%

03Evidence

Inspect the matches

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

Matched commit samples

c5406b05 on GitHubUpdate e2b SDK (js → 2.38.3, python → 2.38.0) (#247)Claude Code
9bbad16f on GitHubfix(ci): tag the version bump, survive push races, release on dispatch (#2Claude Code
8a82ea2f on GitHubchore(ci): pin GitHub Actions to commit SHAs (#241)Claude Code
4bd08fdf on GitHubfix(examples): bump electron to 43.x to resolve extract-zip Dependabot aleDevin
9bea91e8 on GitHubfeat(template): new brand wallpaper and README screenshot (#256)Devin
89a545e2 on GitHubchore: regenerate lock files (#255)Devin
42f017cc on GitHubConfigure Renovate (#142)GitHub Copilot

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	94
Merge commits removed	−0
CI / dependency bots removed	−69
Considered	25

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 →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 e2b-dev/desktop

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	50%	2
2026-03	0%	2
2026-04	100%	2
2026-05	0%	1
2026-06	100%	3
2026-07	50%	4
2026-08	100%	9
2026-09	100%	2