Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
TypeSafe Python SDK (official)
TypeSafe's official client for the hosted Jev API (Python; a matching TypeScript SDK exists). Typed Noul/Choice/Score (and Box) questions over a state; defines the wire format the rest of the community copies.
typesafe-sdk 0.7.5 on PyPI and GitHub release v0.7.5, 2026-10-14; first published 2026-09-09. JS SDK @typesafe-ai/sdk 0.7.0 modified 2026-10-14. (checked 2026-10-25)
In The Jev ecosystem
Where it stands apart
- Can it run entirely on your own device or infrastructure, without the maker's servers? partly (some features need the maker's servers) (19% of 21 others)
- Do you need an account to use it? account required (0% of 21 others)
- Which models answer its questions? Pick the first that applies. only TypeSafe's Jev (direct or through a reseller) (10% of 21 others)
- Which question types does it handle? Jev's three plus extra types (number, excerpt, relation, box, rank...) (14% of 21 others)
- Where do the decisions run by default? a hosted API (24% of 21 others)
- Can you use it without a TypeSafe account? no, a TypeSafe API key is required (5% of 21 others)
What it shares with most of the community
- Is it actively maintained? active (62% of 21 others)
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (86% of 21 others)
- Who is it for? developers (95% of 21 others)
- Which shared standard or format does it mainly build on? TypeSafe's System One API (state + typed questions, /v1/systemone) (81% of 21 others)
- Does it train on Jev's outputs? (TypeSafe's customer agreement forbids using output to distill or build competing models.) it doesn't train models (68% of 19 others)
- Are its answers typed values rather than generated text? (identity question) yes, typed answers only (67% of 21 others)
Nearest neighbors
- System One Adapter (official) 63% of 16 shared answers match
- decide 56% of 16 shared answers match
- jev-align (Sutro) 56% of 16 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-25 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) SDK is MIT; the Jev model and service it calls are proprietary. | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads Jev is billed per input token ($0.042/Mtok). | source 2026-10-25 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | stands apart partly (some features need the maker's servers) The SDK runs locally but the model is hosted; base_url can point at Kev, Laya, Gutsy or Bud servers, which claim SDK compatibility. | source 2026-10-25 |
| Do you need an account to use it? | stands apart account required SDK requires TYPESAFE_API_KEY from a TypeSafe account (early access). | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | TypeSafe's System One API (state + typed questions, /v1/systemone) Reference implementation of the format. | source 2026-10-26 |
| Which models answer its questions? Pick the first that applies. | stands apart only TypeSafe's Jev (direct or through a reseller) | source 2026-10-25 |
| What is the main thing it ships? | a library, CLI, or SDK for calling models | source 2026-10-25 |
| Which question types does it handle? | stands apart Jev's three plus extra types (number, excerpt, relation, box, rank...) Noul, Choice, Score plus an experimental Box (image bounding box) primitive behind a 'Danger-Zone-Images' header. | source 2026-10-25 |
| Does it check whether its probabilities can be trusted? Pick the first that applies. | no, it passes probabilities through without measuring them The SDK just returns probabilities and confidence; TypeSafe's docs explain calibration and publish evals at evals.typesafe.ai. | source 2026-10-25 |
| Where do the decisions run by default? | stands apart a hosted API | source 2026-10-25 |
| Does it train on Jev's outputs? (TypeSafe's customer agreement forbids using output to distill or build competing models.) | it doesn't train models | source 2026-10-25 |
| Can you use it without a TypeSafe account? | stands apart no, a TypeSafe API key is required Jev is early access via waitlist; gateways (Vercel, Netlify, OpenRouter, Cloudflare) also resell it, but this SDK targets api.typesafe.ai. | source 2026-10-25 |
| Are its answers typed values rather than generated text? (identity question) | yes, typed answers only | source 2026-10-25 |
| Does it publish head-to-head numbers against Jev? | no published benchmark numbers It is Jev's own client; TypeSafe's own evals are separate (evals.typesafe.ai). | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/typesafe-ai/typesafe-sdk-python · read 2026-10-25
- Package registry · pypi.org/project/typesafe-sdk/ · read 2026-10-25
- Web page · docs.typesafe.ai/api/system-one.md · read 2026-10-25
- Web page · docs.typesafe.ai/confidence.md · read 2026-10-25
- Web page · docs.typesafe.ai/llms.txt · read 2026-10-25
- Web page · docs.typesafe.ai/models.md · read 2026-10-25
- Web page · typesafe.ai/blog/introducing-system-one-models-and-jev · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.