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.

- 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

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
- apple-silicon
- decision-model
- inference
- laya
- local-ai
- machine-learning
- mlx
- modernbert
- system-one
- typed-decisions
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
- 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 - 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
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- 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 - minutessilverstein/minutesMeeting notes: local-first transcription app whose live voice path runs its evaluations through Jev.★ 1,494
Rust - v-modal/awesome-jev-toolsv-modal/awesome-jev-toolsTools only, no articles or models.★ 657