aionedge.
Jev project · Community additions

laya-mlx

mizorewww/laya-mlx

Local runtime: independent MLX port of the Laya checkpoints that runs typed decisions natively on Apple Silicon — 13.4 ms median end-to-end per short English decision, 7.4 ms with the multilingual checkpoint, and zero output tokens, with no PyTorch, Transformers runtime, or cloud API.

View on GitHub ↗Project website ↗
Laya MLX playing Snake — actual decisions, original speed
Demo from the project README · view README ↗
GitHub stars
5,389 as of 2026-09-22
Forks
491
Language
Python
License
Apache-2.0
Created
2026-09-19
Last updated on GitHub
2026-09-22
Built by this developer
mizorewww

What Jev does in laya-mlx

The project describes itself this way: Local runtime: independent MLX port of the Laya checkpoints that runs typed decisions natively on Apple Silicon — 13.4 ms median end-to-end per short English decision, 7.4 ms with the multilingual checkpoint, and zero output tokens, with no PyTorch, Transformers runtime, or cloud API. In the Community additions category, Jev typically decides a single well-defined judgment, such as a label, a score or a yes/no check.

Verification

Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.

Topics

How Community additions projects use Jev

Projects added from community lists and direct submissions. Many are small, single-purpose experiments, which makes them some of the easiest places to see how a Jev question is framed in real code.

Related Jev projects in Community additions

  1. fxvercel-labs/fxCoding agent: ships a `typesafe_permission_reviewer` builtin so the agent's permission decisions run through Jev rather than an LLM call.★ 3,126
    Zig
  2. MemSearch Jev rerankingzilliztech/memsearchCoding-agent memory: an optional Jev reranker asks Noul questions about retrieved Markdown chunks and sorts them by relevance to the query, with bilingual evaluation results.★ 2,640
    Python
  3. DeepSearcher stopping-policy experimentzilliztech/deep-searcherAgentic search: a standalone evaluation uses Jev Noul judgments on accumulated evidence to decide whether to stop or continue within a search-round budget, comparing stopping behavior, evidence recall, and decision cost.★ 8,278
    Python
  4. Search with Jev and Milvusmilvus-io/bootcampSearch engineering: nine runnable notebooks combine Gemini embeddings and Milvus retrieval with Jev Noul and Choice judgments, while Python applies ranking, filtering, routing, and stopping policies to synthetic examples.★ 2,445
    Jupyter Notebook
  5. minutessilverstein/minutesMeeting notes: local-first transcription app whose live voice path runs its evaluations through Jev.★ 1,494
    Rust
  6. v-modal/awesome-jev-toolsv-modal/awesome-jev-toolsTools only, no articles or models.★ 657

See all 156 Community additions projects →

Where we found it