jevbooks

← All projects

laya-server

pambrose/laya-server

Jev-compatible API server backed by local Laya checkpoints.

Infra / SDKs / Integrations0.93Runner-up: Agent Decisions
Automated README summary

Automatically summarized from the README on 22 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A proof-of-concept server implementing TypeSafe's Jev API, letting Jev clients send state and typed questions and receive calibrated answers from locally run Laya checkpoints instead of a hosted model.

How it uses Jev

Clients POST state and Choice/Score/Noul questions to /v1/systemone; the server routes by language detection to a Laya checkpoint, runs inference, and returns Jev-shaped responses. Oversized input is rejected with 422 rather than silently truncated.

Primitives:choicescorenoul

Technique worth stealing

Rejecting input that exceeds the checkpoint's context window instead of letting Laya truncate it, so answers are never computed on partial data.

Try it

docker run --rm -p 8000:8000 -v laya-checkpoints:/home/app/.cache/huggingface -e LAYA_SERVER_PRELOAD=english pambrose/laya-server:latest

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.73
  • Shows a System One patternnot found in the excerpt0.05
  • Describes handling uncertaintynot found in the excerpt0.04
  • Reports measured numbersnot found in the excerpt0.03
  • Is a runnable toolFound in material0.96
  • Top-10 learning shortlist signalnot found in the excerpt0.18
  • Is a replica of the modelFound in material0.83
  • Solves a common problem (0–2)score on a 0–2 scale0.39 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.73Shows a System One pattern0.05Describes handling uncertainty0.04Reports measured numbers0.03Is a runnable tool0.96Top-10 learning shortlist signal0.18Is a replica of the model0.8300.51Solves a common problem (0–2)0.39 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.64Funnel0.33Inspection0.2000.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 22 Oct 2026.