User repository on GitHub
High-speed, zero-cost System One decision engine powered by Google Gemini (Free Tier), Groq & Ollama. Drop-in alternative to Jev.
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Repos & SDKs
System One Native
A Python decision engine that runs Choice, Noul and Score questions on Gemini's free tier, Groq, OpenAI or a local Ollama server with local response validation. The README calls it a drop-in alternative to Jev and ships agent skill and plugin installs.
- Stars
- 1
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- RodrigoAlbe
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Languages
- Python
- Capabilities
- Open sourceSelf-hostedRuns locally
Highlights
- Use Choice, Noul and Score to classify application state without parsing chat prose, several questions per request.
- Runs on Gemini (free tier), Groq, OpenAI or a local Ollama server, with local response validation.
- Described as a drop-in alternative to Jev; no public PyPI release, install from GitHub with pip and optional commit pinning.
- Also ships as an agent skill (npx skills add RodrigoAlbe/system-one) and a Claude Code plugin.
- README caution: decisions remain probabilistic — valid JSON does not guarantee a correct classification.
Quickstart
bash
python -m pip install "git+https://github.com/RodrigoAlbe/system-one.git"Watch out
README and GitHub metadata reviewed 2026-10-17; the digest stops mid-command in the plugin validation section, so the full API surface, provider configuration and any benchmarks are not captured. The zero-cost claim rests on free tiers and local models.
Questions about this entry
Short answers drawn from the linked project or page.
A Python package from RodrigoAlbe that performs structured AI decisions — Choice, Noul and Score questions — across Gemini, Groq, OpenAI or a local Ollama server, with local response validation.
The GitHub description calls it a high-speed, zero-cost System One decision engine and a drop-in alternative to Jev; it classifies application state without parsing chat prose, using the same typed-question pattern.
Google Gemini (free tier), Groq, OpenAI and a local Ollama server, per the README's description and installation sections.
python -m pip install with the git+https URL of the repository; there is no public PyPI release, and appending @<commit-sha> pins a revision. Git and Python 3.9+ are required.
Yes: npx skills add RodrigoAlbe/system-one --global installs the agent skill, and claude plugin marketplace add plus claude plugin install system-one@system-one installs the Claude Code plugin; the Python library is separate.
That part rests on using free tiers (Gemini) or your own local Ollama server; the digest shows no pricing or rate-limit details beyond that.
The README stresses decisions stay probabilistic: valid JSON does not guarantee that a classification is correct. No benchmarks appear in the captured text, and the digest truncates the maintenance section.
More Jev resources like this
A System One layout optimizer for decision-model workloads: it reorders rows and fields so a prefix-caching backend reuses input computation, then returns per-record decisions in original order. Its bundled backend serves AutoTrust JEV-9B through vLLM.
Jev Repos & SDKs#community#github#python
Community
0814wdwd/solo_jevPython
0814wdwd/solo_jevPythonHTTP 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 frozen decision server that serves Gemma 4 31B — quantized to FP8 at startup — in TypeSafe's /v1/systemone format, reading the next-token distribution instead of generating tokens. It needs one FP8 NVIDIA GPU with 80 GB and has no authentication.
Jev Repos & SDKs#community#github#python
Community
krishna-gogineni-765/deck31bPython
krishna-gogineni-765/deck31bPythonAn open-source, non-autoregressive System One decision engine inspired by TypeSafe AI: it evaluates state context against typed questions in a single forward pass, returning probability distributions and calibrated confidence without generating text.
Jev Repos & SDKs#community#github#python
Community
Atulmishra22/jev-litePython
Atulmishra22/jev-litePythonA Bangla-focused adaptation of Laya, the non-autoregressive typed-decision model: targeted data preparation, fine-tuning and evaluation for classification, routing and scoring on Bangla, Banglish and code-switched text, with the checkpoint still to come.
Jev Repos & SDKs#community#github#python
Community
shamspias/laya-banglaPython
shamspias/laya-banglaPythonFrom 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.