- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
NEO Emacs (WIP): GPU powered Emacs written in Rust with a modern display engine. Aiming for modern design & multi-threaded Elisp, 10x performance, zero-pause concurrent GC and 100% Emacs compatibility.
01Result
eval-exec/neomacs ↗eval-exec/neomacs AI coding statistics: 0.2%
One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
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
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-02 | 0% | 5261 |
| 2026-03 | 0% | 1834 |
| 2026-04 | 1% | 2035 |
| 2026-05 | 0.3% | 4756 |
| 2026-06 | 0% | 3935 |
| 2026-07 | 0.1% | 1801 |
| 2026-08 | 0.1% | 1948 |
| 2026-09 | 0.2% | 878 |
Peak month: 1%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| GitHub Copilot | GitHub | 35 | 0.2% |
| Claude Code | Anthropic | 4 | 0% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
5ec517f0on GitHubFix workflow lint by installing Go before actionlintGitHub Copilotd8b870afon GitHubFix release archive compile failure in tab-bar layout test (#172)GitHub Copilot8750450don GitHubHonor coding-string ASCII NOCOPY fast pathGitHub Copilotc6035189on GitHubCompare byte-code objects slot-wise in equal and sxhash, like GNU's PVEC_CClaude Code66b7a5beon GitHubfix(syntax): keep back_comment from taking a comment char inside a stringClaude Code54ca626eon GitHubci: switch runner to self-hostedClaude Code
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 | 22,687 |
| Merge commits removed | −154 |
| CI / dependency bots removed | −85 |
| Considered | 22,448 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
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 eval-exec/neomacs