User repository on GitHub
An open-source, local, cross-platform runtime for System One models, providing a Jev-compatible API.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Repos & SDKs
System One (native runtime)
An open-source, local-first and cross-platform runtime for System One decision models that exposes a Jev-compatible POST /v1/systemone API and a native CLI without Python, PyTorch, Transformers, Conda or a virtual environment.
- Stars
- 0
- Language
- Rust
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- LiteVar
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is System One — iamaamir.
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- Rust
- Capabilities
- Open sourceRuns locally
Highlights
- Exposes a Jev-compatible POST /v1/systemone API plus a native CLI, with no Python, PyTorch, Transformers, Conda or virtual environment required.
- The first backend is Laya Multilingual; the public API is intentionally model-independent, with Laya implementing the DecisionModel abstraction.
- Release 0.1.1 contains a native tokenizer, Laya decision head, model cache, managed llama.cpp provisioning and dynamic llama.cpp FFI.
- First run downloads pinned model assets and a pinned CPU, Metal or Vulkan llama.cpp runtime for the platform, kept resident for the process lifetime.
- Smoke-tested end to end on macOS arm64; the README states it is independent and unaffiliated with TypeSafe AI.
Watch out
README reviewed 2026-10-17; the status section is cut at the docs/laya-runtime.md link, so installation commands are not captured, and the README says hardware-backend and reference-vector validation remain release-checklist items. MIT licensed, pushed 2026-10-14.
Questions about this entry
Short answers drawn from the linked project or page.
An open-source, local-first, cross-platform runtime for System One decision models. It exposes a Jev-compatible POST /v1/systemone API and a native CLI without needing Python, PyTorch, Transformers, Conda or a virtual environment.
It serves a Jev-shaped API at POST /v1/systemone, so tools written against that interface can call it; the README stresses the project is independent and not affiliated with or endorsed by TypeSafe AI or Jev.
The first backend is Laya Multilingual, but the public API is intentionally model-independent: Laya is one implementation of a DecisionModel abstraction, so other decision-model backends can be added.
A native tokenizer, Laya decision head, model cache, Jev-shaped API, CLI, managed llama.cpp provisioning and dynamic llama.cpp FFI, per the README's status section.
No. The runtime is native and explicitly avoids Python, PyTorch, Transformers, Conda and virtual environments; on first run it downloads pinned model assets and a pinned llama.cpp runtime for the platform.
A pinned CPU, Metal or Vulkan llama.cpp runtime is provisioned per platform, and the native path is smoke-tested end to end on macOS arm64; cross-platform CI checks compilation only, with hardware validation still on the release checklist.
It is published by LiteVar under the MIT license; the Rust repository was created 2026-09-22 and last pushed 2026-10-14, with zero stars at sweep time.
More Jev resources like this
Laya GGUF inference and an HTTP server written in Goish Rust: one Linux binary runs upstream Laya or OpenThai-SystemOne on your CPU and serves typed choose, score and check decisions over HTTP, the CLI or a JSON-lines process.
Jev Repos & SDKs#community#catalog-import#madewithjev
Community
cogentica-ai/laya-goishRust
cogentica-ai/laya-goishRustA 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/ollayaRustTurn markdown into a knowledge graph with an ontology you write and a cutoff you own. A local decision model answers closed yes-or-no questions one at a time, and anything it is unsure about waits for a person instead of entering the graph.
Jev Repos & SDKs#community#github#rust
Community
raphaelmansuy/edgextractTypeScript
raphaelmansuy/edgextractTypeScriptHTTP server for the Mica v0.5 4B Preview decision model: GGUF weights run through llama.cpp and answer noul, choice and score questions with calibrated probabilities over the TypeSafe /v1/systemone format.
Jev Repos & SDKs#community#github#python
Community
akivet/MicaPython
akivet/MicaPythonServing code for the Jeff 1.0 family of Jev-style decision models: a state, a typed question and its options go in, and one forward pass returns a probability for each option. Four open models from 4B to 31B parameters are served the same way.
Jev Repos & SDKs#community#github#python
Community
j-geuter/jeff-servePython
j-geuter/jeff-servePythonA native Swift implementation of OpenJev, the Jev-compatible typed-decision server: send a state and typed questions over a Jev-compatible HTTP API and read every answer from model probabilities, on Apple silicon Macs or inside iPhone and Mac apps.
Jev Repos & SDKs#community#catalog-import#cobanov
Community
algorythm-canada/openjevswiftSwift
algorythm-canada/openjevswiftSwiftFrom 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.