Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
System One Adapter (official)
TypeSafe's drop-in replacement for the SDK's system_one call, backed by OpenAI-compatible, Anthropic or Gemini LLMs, so you can compare Jev to an LLM on cost, speed and accuracy.
Last release v0.2.1 and last push 2026-09-22 (PyPI system-one-adapter 0.2.1, same day); no activity in the five weeks since. (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)
- Where do the decisions run by default? a hosted API (24% of 21 others)
- Can you use it without a TypeSafe account? yes, through a gateway or another provider (24% of 21 others)
- Are its answers typed values rather than generated text? (identity question) typed answers, but generated text is part of the pipeline (14% of 21 others)
What it shares with most of the community
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (86% of 21 others)
- Do you need an account to use it? no account (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)
- Which models answer its questions? Pick the first that applies. other models, not Jev (open, local, or LLMs) (52% of 21 others)
- Which question types does it handle? Jev's three: noul, choice, score (67% 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)
Nearest neighbors
- decide 75% of 16 shared answers match
- jev-align (Sutro) 75% of 16 shared answers match
- jevper 75% of 16 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | maintenance or slowing | source 2026-10-25 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) MIT | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads Published by TypeSafe AI as a comparison tool for its paid API. | 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) Runs locally but calls LLM provider APIs; an OpenAI-compatible local server would make it fully local. | source 2026-10-25 |
| Do you need an account to use it? | no account Needs an LLM provider key, not an account with the maker. | 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) Mirrors typesafe_sdk's system_one API. | source 2026-10-26 |
| Which models answer its questions? Pick the first that applies. | other models, not Jev (open, local, or LLMs) Official, but its purpose is to answer the same questions with an LLM instead of Jev. | 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? | Jev's three: noul, choice, score | 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 llm_answer_mode='probabilities' asks the LLM for verbalized probabilities and normalizes them. | source 2026-10-25 |
| Where do the decisions run by default? | stands apart a hosted API LLM provider APIs by default. | 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 yes, through a gateway or another provider Needs an LLM provider key, not a TypeSafe key. | source 2026-10-25 |
| Are its answers typed values rather than generated text? (identity question) | stands apart typed answers, but generated text is part of the pipeline The LLM generates structured output that is parsed into typed answers. | source 2026-10-25 |
| Does it publish head-to-head numbers against Jev? | no published benchmark numbers Built for comparison, but the README publishes no numbers; TypeSafe's WorkflowEvals repo does. | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/typesafe-ai/system-one-adapter-python · read 2026-10-25
- Package registry · pypi.org/project/system-one-adapter/ · read 2026-10-25
- Web page · docs.typesafe.ai/models.md · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.