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 desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents.

01Result

deer-flow/llm-space ↗

deer-flow/llm-space AI coding statistics: 6.8%

of 710 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

6.8% agent · top contributor 85.4%5 contributors

individual

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

agent commits

662

other considered commits

agent contributors

85.4%

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

48assisted

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: 10.5%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	44	6.2%
OpenAI Codex	OpenAI	3	0.4%
GitHub Copilot	GitHub	1	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

5e86bc8e on GitHubfix(runtime): write edit tool replacements literallyClaude Code
b0f9f59c on GitHubfix(core): keep tool result errors when importing threadsClaude Code
57899ee7 on GitHubfix(runtime): keep apply_patch insertion-only hunks at the end of the fileClaude Code
e9401d32 on GitHubchore: prepare 4.6.1 releaseOpenAI Codex
c345e635 on GitHubchore: prepare 4.6.0 releaseOpenAI Codex
6d79ec45 on GitHubfix(skills): support multiline frontmatter descriptionsOpenAI Codex
18d2c58d on GitHubfeat: add Seedream image generation and provider profiles (#125)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	774
Merge commits removed	−59
CI / dependency bots removed	−5
Considered	710

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 deer-flow/llm-space

Scan another repository

Try

Month	Agent share	Considered commits
2026-06	0%	89
2026-07	10.5%	401
2026-08	1.2%	164
2026-09	7.1%	56