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.

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

01Result

mirage-project/mirage ↗

mirage-project/mirage AI coding statistics: 36.4%

of 66 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

Too little recent activity to publish. Only 66 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.

36.4% agent · top contributor 29.2%10 contributors

org-wide

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

agent commits

other considered commits

agent contributors

29.2%

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

24assisted

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: 83.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	19	28.8%
Cursor Agent	Anysphere	4	6.1%
GitHub Copilot	GitHub	1	1.5%

03Evidence

Inspect the matches

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

Matched commit samples

110c9f49 on GitHubfix(argmax): bound the reduction to the real vocab size (#758)Claude Code
176042f5 on GitHubfix(argmax): pad lm_head rows with -1e4 instead of 0 (#755)Claude Code
43740085 on GitHubgpt-oss: drop --save-tokens from the demoClaude Code
0cd41ecf on GitHubfix: add MoE residual on every rank when it is a TP partial sum (#753)Cursor Agent
c9d83035 on GitHubtest: add MoE residual double-count regression test (null-residual path) (Cursor Agent
8de1cfc2 on GitHubFix double-counted MoE residual under tensor parallelism (#722)Cursor Agent
c004c0b5 on GitHubtest: improve test mode interface (split from dpskv3) (#712)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	68
Merge commits removed	−2
CI / dependency bots removed	−0
Considered	66

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 →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 mirage-project/mirage

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	8
2026-03	0%	3
2026-04	21.4%	14
2026-05	0%	3
2026-06	44.4%	18
2026-07	75%	4
2026-08	83.3%	12
2026-09	0%	4