Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
OpenDecision
Local typed decisions over text, documents and images using off-the-shelf zero-shot models (ModernBERT/DeBERTa NLI, SigLIP2), with a FastAPI server that is TypeSafe-SDK compatible; ~2 GB RAM on CPU.
PyPI OpenDecision 0.2.0 and GitHub release v0.2.0 on 2026-10-11; repo pushed 2026-10-15. (checked 2026-10-25)
In The Jev ecosystem
Where it stands apart
- Which shared standard or format does it mainly build on? none of these (its own format or interface) (14% of 21 others)
- What is the main thing it ships? a runtime, server, proxy, or desktop app for running models (24% of 21 others)
- Which question types does it handle? Jev's three plus extra types (number, excerpt, relation, box, rank...) (14% of 21 others)
- Does it publish head-to-head numbers against Jev? benchmarks, but not against Jev (19% 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)
- How is it mainly sustained? individual side project, no revenue (55% of 20 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (52% 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 models answer its questions? Pick the first that applies. other models, not Jev (open, local, or LLMs) (52% 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)
- Can you use it without a TypeSafe account? yes, no TypeSafe account involved (62% of 21 others)
- Are its answers typed values rather than generated text? (identity question) yes, typed answers only (67% of 21 others)
Nearest neighbors
- snap 81% of 16 shared answers match
- jeva.cpp 75% of 16 shared answers match
- Bud Decision Studio 63% 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) Apache-2.0 | source 2026-10-25 |
| How is it mainly sustained? | individual side project, no revenue Personal repo, free open source, no pricing. | source 2026-10-26 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes | source 2026-10-25 |
| Do you need an account to use it? | no account Local CPU server; no account. | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | stands apart none of these (its own format or interface) Own Python API first; a TypeSafe-SDK-compatible endpoint is secondary. | source 2026-10-26 |
| Which models answer its questions? Pick the first that applies. | other models, not Jev (open, local, or LLMs) | source 2026-10-25 |
| What is the main thing it ships? | stands apart a runtime, server, proxy, or desktop app for running models Wraps existing zero-shot models rather than releasing new weights. | source 2026-10-25 |
| Which question types does it handle? | stands apart Jev's three plus extra types (number, excerpt, relation, box, rank...) Adds Relation (supports/contradicts/unknown/conflicted), documents and images. | 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 README: 'Model scores are uncalibrated.' | source 2026-10-25 |
| Where do the decisions run by default? | on your own hardware (CPU, Mac, or GPU) | 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? | yes, no TypeSafe account involved | 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? | stands apart benchmarks, but not against Jev Own synthetic claim and GDPR retrieval benchmarks. | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/deepanwadhwa/OpenDecision · read 2026-10-25
- Package registry · pypi.org/project/OpenDecision/ · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.