User repository on GitHub
Scaffold project for Jev Impl as a gateway Integration layer
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Jev Gateway Integration Scaffold
Scaffold project for implementing Jev as a gateway integration layer, demonstrated by a FastAPI service that answers weather questions for a City/State: an SLM works out intent, location and date, Open-Meteo supplies facts, and an LLM writes the answer.
- Stars
- 0
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- rogerwtrimble-tech
- Last verified
- Oct 2026
Used inJev for Software & DevTools
Highlights
- Described as a scaffold project for a Jev implementation as a gateway integration layer, built as a FastAPI service.
- Pipeline: question to SLM router (intent, location, date) to Open-Meteo facts to an LLM that answers from retrieved facts only.
- Default question: 'Is it currently hot in [City/State] for this time of the year?'
- Every stage has a fallback, so a fresh clone runs with no configuration: rule-based router without an SLM, built-in answer template without an LLM.
- Quick start: make install, make env, make run, then http://localhost:8000/docs.
Quickstart
bash
git clone <this repo> && cd jev
make install
make env
make runWatch out
README and GitHub metadata reviewed 2026-10-17; the captured README documents the weather service pipeline and never mentions TypeSafe or a Jev API call, so the Jev connection rests on the repository name and description. The curl example is truncated in the digest.
Questions about this entry
Short answers drawn from the linked project or page.
A scaffold project for implementing Jev as a gateway integration layer, per the repository description; the captured README presents it as a FastAPI weather-question service.
An SLM reads the question and extracts intent, location and date, Open-Meteo supplies live conditions plus 30 years of history as JSON facts, and an LLM writes the final answer using only the retrieved facts.
Is it currently hot in the given City/State for this time of the year?
Yes. Each stage has a fallback: without an SLM it uses a rule-based router, and without an LLM it uses a built-in answer template, so a fresh clone runs with no keys, per the README.
Quick start per the README: git clone the repo, run make install for the venv and dependencies, make env to create .env from .env.example, then make run and open http://localhost:8000/docs.
It does not. The captured README covers the weather pipeline and never mentions TypeSafe or a Jev API call, so what the scaffold implements beyond this pattern is unverified in the digest.
A Python repository with 0 stars, created and pushed 2026-10-04, with no licence listed in the digest metadata and no benchmarks captured.
More Jev resources like this
A Chinese-language e-commerce customer-service demo on FastAPI, LangGraph and React: adaptive retrieval routing with hybrid BM25-plus-vector search, and intent classification switchable between TypeSafe Jev's structured choice interface and DeepSeek.
Jev Demos & Experiments#community#github#python
Community
gbh1234/Adaptive-ragPython
gbh1234/Adaptive-ragPythonTwo Jev demos over SprintPulse QA data: one scores release risk with a 10-level rubric evaluated against a reference score, the other diagnoses the main risk cause with a 9-label choice question, both sending the same per-ticket signals to Jev's System One API.
Jev Demos & Experiments#community#github#python
Community
avi350751/jev-qa-analyzerPython
avi350751/jev-qa-analyzerPythonFinds Dublin buses that are scheduled, due, and just not there: it checks the GTFS timetable against the live vehicle feed and flags trips with no bus and no cancellation. Built in a day for Build for Ireland, live on open data and Jev.
Jev Demos & Experiments#community#github#transit
Community
Rajatgdev/Ghost_busPython
Rajatgdev/Ghost_busPythonAn 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 small FastAPI demo that triages customer support tickets with Jev as the decision layer: one request returns typed answers for department, urgency, refund intent and human-review need, while Python rules route and LangChain can draft a reply.
Jev Demos & Experiments#community#github#fastapi
A small proof-of-concept app that runs local Laya and external System One-family APIs in one judgment UI: it executes typed questions against a state and compares choice probabilities, yes/no probabilities and ordinal scores across providers.
Jev Demos & Experiments#community#github#python
Community
keispace/systemonePython
keispace/systemonePythonFrom 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.