Jev directory
CommunityJev Models & Reimplementations
Jev-RS
Rust decision engine that runs TypeSafe AI's Jev protocol locally: one ONNX forward pass answers noul, choice, and score questions with calibrated probabilities and confidence. Serves a dashboard and the /v1/systemone API on 127.0.0.1:8000.
- Stars
- 0
- Reading time
- 2 min
- Published by
- Community
- Added
- Oct 2026
Highlights
- Rust 1.80+ engine on ONNX Runtime; DirectML GPU on Windows, CPU build elsewhere.
- Downloads a ~2.3 GB pre-exported ONNX model itself, with no Python, torch, or virtualenv.
- Answers noul, choice, and score questions in one batched forward pass with probabilities and confidence.
- Measured 152 ms for eight criteria in one request against 944 ms asked one by one.
- MIT licensed; prebuilt Windows binary ships as jev-rs-windows-x86_64.zip.
Questions about this entry
Short answers drawn from the linked project or page.
No. The model is a pre-exported ONNX bundle that the engine downloads itself, so there is no virtualenv, no torch, and no optimum involved.
The model is roughly 2.3 GB and the download is resumable. If it breaks partway, run the download command again and it continues.
Three: noul returns the probability that the state is true; choice returns the winning option with a full distribution and confidence; score returns an expected value from 1 to N with a distribution and confidence. criteria is mandatory for choice and score.
Malformed criteria are rejected with HTTP 400 instead of being silently coerced. Duplicates are rejected too, because a duplicate would collapse in the probability map while the winner was still chosen over the full list, producing distributions that did not sum to 1.
Windows, Linux, and macOS. Windows builds use DirectML GPU acceleration by default; Linux and macOS build with --no-default-features for CPU inference.
POST /v1/systemone requires the API key when the JEV_API_KEY environment variable is set. Responses carry x-typesafe-request-id and x-response-time-ms headers.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Standard One SH (StandardThinking)
LinkedIn: What multimodal decision models actually change, and what they do not.
LinkedInJevDirectory.org
Hacker News: Decision Index 0.2.1 scores open reproductions of Jev on a frozen suite.
jackbravo4 pointsDecision Index 0.2.1 – 70 open reproductions of TypeSafe Jev's Decision ModelRead the thread on Hacker NewsHacker News: Pointer to a DiffusionGemma plus vLLM tutorial for a Jev-shaped classifier.
1 pointHow to build a Jev-style classifier with DiffusionGemma and vLLMRead the thread on Hacker NewsMore Jev resources like this
A local daemon that pulls open decision models and serves them on TypeSafe's /v1/systemone, so a Jev client switches hosts with TYPESAFE_BASE_URL.
Jev Models & Reimplementations#community#rust#open-models
Community
ollaya-dev/ollayaRust
ollaya-dev/ollayaRustOpen Jev-style decision model built on LiquidAI's LFM2.5-350M backbone, a clone of kev. Serves the System One API contract so the TypeSafe SDK works against a local server, returning probabilities for typed questions from one forward pass.
Jev Models & Reimplementations#open-models#python#local
Communityfranckverrot/lev
A Laya fine-tune from Convai Innovations on the 1,200-case typed-decisions benchmark: it reports 0.777 accuracy on the official 400-case test set, above TypeSafe Jev 1.13.0 at 0.727 and the teacher ceiling at 0.735.
Jev Models & Reimplementations#community#open-models#local
Community
A native MLX runtime for Laya's open typed-decision weights: short decisions on Apple Silicon, with no generated tokens, PyTorch, or cloud API.
Jev Models & Reimplementations#community#python#open-models
Community
mizorewww/laya-mlxPython
mizorewww/laya-mlxPythonAn open-model semantic-if engine positioned as a local Jev-style decision stack, separate from the original SemIf repo but sharing the same author.
Jev Models & Reimplementations#community#python#open-models
Community
TheoLeeCJ/SemIf-OpenJevPython
TheoLeeCJ/SemIf-OpenJevPythonLaya typed decisions through Apple Core ML and the Neural Engine, with the author's speed and energy benchmarks for short decisions on an M3 Max.
Jev Models & Reimplementations#community#python#open-models
Communitymizorewww/laya-coremlPython
mizorewww/laya-coremlPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.