Organization repository on GitHub
Run a JSON Schema through TypeSafe's Jev API, and get JSON back.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Tools & CLIs
Jev Jsonschema
Python layer that converts a JSON Schema into Jev questions and decodes the answers back into JSON that validates against the original schema, with sync and async clients.
- Stars
- 7
- Language
- Python
- License
- MIT
- Published by
- Community
- Author
- Kiln-AI
- Last verified
- Oct 2026
About this project
Use a JSON Schema with Jev. Get JSON back. Quick Start • What Maps to What • What You Get Back • Without the Client • Limits. Jev is a new kind of model from TypeSafe: it only returns structured output, it's blazing fast, and it's cheap. That's great, but it means Jev doesn't speak JSON Schema, and most LLM apps use JSON Schema for structured output. This library sits in between. Give it your schema and your content, and you get back JSON that validates against the schema you started with.
Quoted from the project's README. Read the full README.
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- Python
Highlights
- One question per schema property, in schema order; convert once and reuse the set in a loop.
- Enums map to choice up to 255 options; integer ranges map to score with at most 10 values.
- Returns output, confidence, probabilities, usage, and the raw response.
- Pure converters work without the client for custom HTTP, retries, and auth.
Watch out
One call is one POST with no hidden retries or concurrency, and failures log status plus request id without echoing bodies. 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.
Booleans become thresholded noul, 0-to-1 numbers return the raw probability, string and integer enums become choice, and bounded integer ranges become score. Free-form strings, arrays, objects, null, anyOf, oneOf, allOf, refs, const, and not are rejected before anything is sent.
Each question gets instructions from the property description, falling back to title then property name. A thin key alone is weak evidence, so set instructions_fallback_to_key to False if you would rather reject undescribed booleans and numbers.
Use result.output as validated JSON, plus confidence, probabilities keyed by your schema values, usage token counts, and the raw response. Noul confidence is None because the probability itself is the measure.
Catch IncompatibleSchemaError for unmappable properties, reported for every bad property at once, and JevApiError for transport failures with status_code, retryable, and request_id. One call is one POST, so backoff policy stays in your code.
pip install jev_jsonschema or uv add jev_jsonschema. Both JevClient and AsyncJevClient expose identical methods, and the client reads TYPESAFE_API_KEY or takes an explicit api_key.
Yes. jev.convert(schema) returns a QuestionSet that remembers how each property was mapped, so you call jev.ask(question_set, state=...) per item without redoing the conversion.
MappingOptions lets you set noul_threshold for where a probability becomes True, max_score_levels to lower the integer-range cap, score_decode to argmax or expected, and instructions_fallback_to_key.
More Jev resources like this
34GitHub stars
Pure-HTTP automation for the TypeSafe register, magic-link login, onboarding, and API-key creation flow, with pluggable temp-mail backends, concurrent batch runs, and key verification exports.
Jev Tools & CLIs#community#awesomejev#catalog-import
Community
2951461586/Jev-Register-ToolPython
2951461586/Jev-Register-ToolPython36GitHub stars
Python toolkit plus 0.8B multimodal model that takes a message, document, or image and returns calibrated choice, yes/no, and score answers in one forward pass for local decision workloads.
Jev Tools & CLIs#community#awesomejev#catalog-import
Community
PsiACE/dohnutsPython
PsiACE/dohnutsPython39GitHub stars
Video tool where Jev scores subtitle segments and code assembles a short highlights cut plus a de-watered full cut with timestamped summaries.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
cclank/jevclipPython
cclank/jevclipPython30GitHub stars
Forkable weekday radar that asks Jev one yes-or-no question per interest over each new arXiv announcement and publishes a page plus RSS feed.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
Eliot5566/JEV-Paper-RadarPython
Eliot5566/JEV-Paper-RadarPython38GitHub stars
Async supervisory layer for Hermes Agent that locks Definitions of Done, proves mechanical criteria locally, and calls Jev only for unresolved semantic checks under a token budget.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
keeltrace/hermes-nervePython
keeltrace/hermes-nervePython15GitHub stars
Two-tier decision engine pairing a 22.6M-parameter MiniLM encoder on the Apple Neural Engine with the on-device Apple Foundation Model as fallback for uncertain inputs.
Jev Tools & CLIs#community#awesomejev#catalog-import
Community
kerryrm/systemANEPython
kerryrm/systemANEPythonFrom 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.