User repository on GitHub
Everything related to system one models
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
System One Lab (Laya + LangGraph)
A Streamlit lab that places a bounded System One decision inside a coding-agent workflow: Laya classifies CI failures, LangGraph applies a fallback policy, and an OpenAI agent inspects a fixture repo and proposes a fix.
- Stars
- 0
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- natenberenstein
- Last verified
- Oct 2026
Highlights
- Laya routes CI failures into code_bug, environment, test_flake or unknown before LangGraph dispatches the result.
- A probability cutoff sends low-confidence cases to an OpenAI second judgment, which is then dispatched too.
- The demo compares Laya, Laya plus fallback, OpenAI-only and keyword rules on the same eight cases.
- Shows accuracy, model calls, token usage, stage timing and the effect of different probability cutoffs.
- The LangChain/OpenAI agent reads a fixture repo and runs the failing test; its tools are read-only.
Watch out
README reviewed 2026-10-17; the captured excerpt describes the workflow and mermaid diagram but cuts off inside the diagram, so setup, the Laya provider, API-key requirements and full results are not visible. The repo is named systemone but never names Jev or TypeSafe in the captured text.
Questions about this entry
Short answers drawn from the linked project or page.
A Streamlit application that demonstrates a bounded System One decision inside a coding-agent workflow, using Laya to classify CI failures and LangGraph to dispatch a fallback policy.
Laya classifies each failure as code_bug, environment, test_flake or unknown, and the app displays its chosen probability alongside the route.
If Laya's probability is below a cutoff, an OpenAI model gives a second judgment; whether Laya is accepted or the fallback is used, LangGraph dispatches the result.
It compares Laya, Laya plus OpenAI fallback, OpenAI-only and simple keyword rules on the same eight cases, reporting accuracy, model calls, token usage, stage timing and cutoff effects.
The captured README never names Jev or TypeSafe and does not say where Laya comes from; it frames the work as a System One decision, so a direct Jev connection is not established by the digest.
For a reproducible code failure, a LangChain/OpenAI agent reads a small fixture repository, runs the specific failing test and proposes a fix; its tools are read-only, so it does not modify the fixture.
The repository belongs to natenberenstein, is Python, has 0 stars and 0 forks, and was created and last pushed on 2026-09-28. No licence is listed in the digest.
More Jev resources like this
Eleven small runnable projects for learning Jev and other System One decision models, each lesson pairing a one-command web demo with a whiteboard and README, from the three question types through jobs sorting and contract review to Jev inside a SQL query. Every demo makes live API calls.
Jev Demos & Experiments#community#github#python
Community
aianytime/jev-crash-coursePython
aianytime/jev-crash-coursePythonA 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-ragPythonA small Python app that asks whether a headline is Onion-style satire or real news. Jev runs through TypeSafe's API with your own key and is compared side by side with AnyJev L0 and raw Qwen3-8B running locally, with an option to swap the answer order.
Jev Demos & Experiments#community#github#python
Community
andrisgauracs/onion-or-notPython
andrisgauracs/onion-or-notPythonDemo pack from the French-language Jev meetup of 8 October 2026 on System One models: a Chrome ad-blocker, an unclutter browser fork, a decision-routing kit comparing a local engine with Jev via OpenRouter, and n8n email triage.
Jev Demos & Experiments#community#github#demos
Community
royam0820/Jev-MeetupJupyter Notebook
royam0820/Jev-MeetupJupyter NotebookA Python dispatcher skeleton for TypeSafe System One (Jev) that turns typed signatures into batched questions, plus a Playwright browser harness that measures the dispatcher against ground truth.
Jev Demos & Experiments#community#github#python
Community
monkey1sai/jev-systemone-labPython
monkey1sai/jev-systemone-labPythonA Python web app that sends every support ticket to Jev (typesafe/jev-1.13) and to configured comparison models through OpenRouter, showing team routing, urgency, severity, sentiment and draft replies side by side with latency and cost.
Jev Demos & Experiments#community#github#python
Community
nikojim/jevPython
nikojim/jevPythonFrom 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.