User repository on GitHub
AI defect code suggestions for Non-Conformance Reports, powered by TypeSafe AI's Jev model
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Tools & CLIs
Jev Ncr Demo
Rust Leptos and Axum demo that sends an NCR description to Jev as state with one yes-or-no question per defect code, then sorts suggestions by confidence.
- Stars
- 1
- Language
- Rust
- Published by
- Community
- Author
- Alexandre-Borghi
- Last verified
- Oct 2026
About this project
This demo app shows how TypeSafe AI's Jev model can be used to assign defect codes to a Non-Conformance Report from a short description written by an operator. This is not a full-fledged app, it is meant to illustrate how Jev could be used in an industrial setting. System One model: a model designed to make fast, structured decisions. Send state and typed questions: to use the model, give it some data and a set of questions to answer (Yes/No, Choice or Score).
Quoted from the project's README. Read the full README.
Highlights
- One Jev call per description edit, with state as NCR text and noul questions from defect_codes.json.
- Probabilities sorted by confidence with threshold auto-checking, still operator-editable.
- Server-side-rendered Rust stack using Leptos with Axum from the start-axum template.
- Runs locally with TYPESAFE_API_KEY; missing key shows an error only in the AI feature.
Watch out
Afternoon demo, not production-grade; only the defect-code suggestion works and other UI panels are illustrative mocks. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
No. Suggestions above threshold come pre-checked, but the operator can remove or add codes. It is suggestion only, built to show industrial use rather than replace review.
A hand-written single-file client generated from the API docs, since only Python and JavaScript SDKs existed. See src/ncr.rs for Jev use and src/typesafe.rs for the call.
Set TYPESAFE_API_KEY and run cargo run for the app on 127.0.0.1:3000. Without a key the app still starts but the analysis feature shows an error.
No timing or cost comparison is included yet. The author lists benchmarking against a small LLM doing the same task as future work.
When the NCR description changes, it calls the model with the description as state and a yes/no question for every defect code. It returns a probability per code, sorts suggestions by confidence, and auto-checks those above a threshold; the operator can still add or remove codes.
Rust with Leptos and Axum together as a server-side-rendered app, started from the Leptos start-axum template. The TypeSafe HTTP client is a single generated Rust file in src/typesafe.rs, since only Python and JavaScript SDKs were official at the time.
No. The author calls it a simple demo vibe-coded over an afternoon, not production-grade. The only working feature is the AI defect code suggestion, and the other UI panels exist to show how it could be integrated into a larger solution.
More Jev resources like this
1GitHub stars
Experimental desktop SAST app that asks Jev reviewable questions about bounded source regions, with Rust handling inventory, bounds, hashing, consent, and persistence.
Jev Tools & CLIs#community#github
Community
turenlabs/jastRust
turenlabs/jastRust3.5kGitHub stars
An Elasticsearch-compatible autoindex search layer that optionally sends top hits to TypeSafe Jev and reorders results by relevance scores.
Jev Tools & CLIs#community#rust#search
Community
xerj-org/xerjRust
xerj-org/xerjRust376GitHub stars
Claude Code Trace renders the JSONL session files in ~/.claude/projects/ as browsable conversations with expandable tool calls, MCP tool names, and token counts, with an optional Jev pass that scores agent efficiency.
Jev Tools & CLIs#community#jevbest
Community
delexw/claude-code-traceRust
delexw/claude-code-traceRust56GitHub stars
R.A.I.N. Lab is a local-first research environment. Four constrained perspectives investigate a question, quoted spans are checked against a local paper corpus, and experiments are pre-registered with host code, not a model, deciding pass, fail or inconclusive.
Jev Tools & CLIs#community#jevbest
Community
topherchris420/james_libraryRust
topherchris420/james_libraryRust51GitHub stars
Docker Compose log intelligence stack: Rust ingest and retrieval crates over ClickHouse and Qdrant with a Next.js dashboard, where the decision model is an optional query classifier.
Jev Tools & CLIs#community#jevbest
Community
YEDASAVG/StratumRust
YEDASAVG/StratumRust30GitHub stars
Rust CLI that checks each PDF page for a usable text layer, extracts text pages locally, sends only the rest to an OCR model via LiteLLM, and merges a page-ordered result.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
misbahsy/doc-routerRust
misbahsy/doc-routerRustFrom the Jev guides
Original write-ups on what this entry is for.
The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.
Jev Tools & CLIs#gateway#vercel#cloudflare
Read article
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.
Jev Tools & CLIs#classification#email#security
Read article
From the Jev community
Posts from builders shipping with Jev right now.