All decision model projects

Open multilingual System 1 decision engine built on Laya checkpoints with a router that picks the best checkpoint per request.

Nace.AI's open Drex decision models (v2.0 MoE, v1.5 9B, diffusion DLM) serving /v1/systemone locally via Python, llama.cpp or Ollama.

Self-hosted open Jev implementation: SDK and System One API for choice, boolean and score on pinned open models across many runtimes.

Python library for one-line judgment calls (likely, classify, rate) returning YES, NO or UNSURE, built for Jev and other small models.

Apache-2.0 local decision model (0.8B Qwen fine-tune on llama.cpp) behind the Jev request shape, calibrated and CPU-only.

Small open vision-language decision models (2B, 4B, 9B) that answer typed questions about photos and records with a trained can't-tell.

0.8B open System One model with task adapters that makes millisecond decisions in front of a larger local model like Qwen3.8-27B.

Self-hosted drop-in replacement for Jev's System One API, powered by the 400M-parameter GLiFormer model.

Workbench where Jev sorts training records into keep, review or reject, then trains LoRA adapters and evaluates them.

Local /v1/systemone server in Japanese docs with LFM, Sarashina and fine-tuned ModernBERT-Ja backends, including image input.

Local MCP server giving Claude Code, Codex, Cursor and OpenCode per-dimension Jev quality scores on their code while they work.

Minimal grammY Telegram bot that asks Jev whether each group message is spam and deletes only high-confidence matches.

AutoTrust's Apache-2.0 student of Jev 1.13 on Qwen3.8-27B, serving typed decisions and ordinary generation from one vLLM engine.

AutoTrust's vision version of JEV-27B, ranked first of 20 on the community Jev Decision Index vision board.

Agent skill that sends closed coding-agent judgments to Jev before asking the user, before risky commands and after failures.

Local Jev-compatible /v1/systemone server answering Noul, Choice and Score from open-weight models, usable with the official SDK.

Rust engine that answers noul, choice and score from any LLM in one prefill via logprobs, wire-compatible with /v1/systemone and MCP.

Open 0.8B and 2B Qwen3.5 decision models with a local systemone-compatible server, MCP tools, agent skills and a Claude Code guard.

Single-binary local cache that memoizes Jev-class decisions on model, schema and redacted state, for cheap repeats and CI replay.

Makes any logprob-capable model answer typed questions Jev-style in one pass, in Jev's API shape, with probes and scorecards.

Scores every allowed option of a typed schema from one MLX prefill on Apple Silicon and assembles schema-valid JSON with probabilities.

Small open decision models (0.8B and 4B, from Qwen3.5) with a server that speaks Jev's /v1/systemone format in one forward pass.

Semantic linter that evaluates files against plain-English JSON rule packs in one /v1/systemone pass, locally with Kev or remotely with Jev.

Node.js and TypeScript package that runs Laya through ONNX Runtime with typed answers matching the Python and Jev API shapes.

Runs Laya's typed-decisions checkpoint on Mac GPUs via PyTorch MPS, with a low-memory mode down to about 0.74 GiB.

Fork of Laya that runs its choice, score and yes/no decision checkpoints on Huawei Ascend 910B NPUs as well as CPU.

Toolkit that turns Laya into a task specialist: LLM-generated and verified training data, RLCD training, calibration and longer context.

Independent MLX port of Laya for Apple Silicon: typed decisions in about 13 ms (7 ms multilingual) with no PyTorch or cloud API.

From-scratch Rust reimplementation of Laya on candle, including the encoder, decision head, calibration, RLCD training and a server.

CPU-first Rust runtime and HTTP server for Laya's multilingual model on ONNX Runtime, with portable builds and Chinese and English docs.