Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
THX-01 (HAL-X AI)
322M mmBERT-based multilingual decision model (Azerbaijani emphasis) trained with RL for calibrated decisions; Apache weights, a pip server with a TypeSafe-compatible alias, and a free hosted API.
Hugging Face model created 2026-09-23, last modified 2026-10-16; PyPI thx01 1.0.0 on 2026-10-08. Posted to Show HN four times, claiming to beat Jev. (checked 2026-10-25)
In The Jev ecosystem
Where it stands apart
- How is it mainly sustained? company or startup with a free product (no revenue yet) (5% of 20 others)
- What is the main thing it ships? model weights (19% 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? no default: you choose a local or hosted backend (14% 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)
- 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 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)
- 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)
Not documented
The public sources we read don't say:
- Does it train on Jev's outputs? (TypeSafe's customer agreement forbids using output to distill or build competing models.)
Nearest neighbors
- Kev 80% of 15 shared answers match
- Laya 80% of 15 shared answers match
- Gutsy 73% of 15 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? | stands apart company or startup with a free product (no revenue yet) HAL-X AI; free API at api.hal-x.ai, no pricing seen. | source 2026-10-25 |
| 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 Open weights and a pip server run locally; no account needed. | 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) /v1/decide with a /v1/systemone alias, 'TypeSafe-compatible'. | 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 model 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 number, excerpt and cite as native types. | source 2026-10-25 |
| Does it check whether its probabilities can be trusted? Pick the first that applies. | yes, it publishes calibration metrics (ECE, Brier, or similar) | source 2026-10-25 |
| Where do the decisions run by default? | stands apart no default: you choose a local or hosted backend Self-hosted weights or HAL-X's free 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.) | Not documented About 2.1M training decisions; their source is not stated. | 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 Excerpts are verbatim spans, not generated text. | source 2026-10-25 |
| Does it publish head-to-head numbers against Jev? | yes, head-to-head numbers against Jev | source 2026-10-25 |
Sources
This page was derived from:
- Package registry · huggingface.co/doofz/THX-01 · read 2026-10-25
- Package registry · pypi.org/project/thx01/ · read 2026-10-25
Are you a maintainer? Claiming and correcting projects is coming soon.