Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
Laya
Multilingual, non-autoregressive System 1 decision engine on ModernBERT/mmBERT (322M-421M params), trained with RL against proper scoring rules, with a router across checkpoints; Python, TypeScript/ONNX, MCP and a /v1/systemone server.
PyPI laya 0.4.15 and GitHub release v0.4.15 on 2026-10-24; repo created 2026-09-18, pushed 2026-10-25; 34k stars, the most-starred community project. (checked 2026-10-25)
In The Jev ecosystem
Where it stands apart
- What is the main thing it ships? model weights (19% of 21 others)
- Does it train on Jev's outputs? (TypeSafe's customer agreement forbids using output to distill or build competing models.) it trains models, but not on Jev's outputs (21% of 19 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)
- Which question types does it handle? Jev's three: noul, choice, score (67% 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)
Nearest neighbors
- Kev 94% of 16 shared answers match
- Gutsy 88% of 16 shared answers match
- THX-01 (HAL-X AI) 80% 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 code and weights. | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads Laya is free, from Convai Innovations (CEO is author), which sells Nadhi Audit at $600/yr. | 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 Self-hosted weights and server; optional self-set LAYA_API_KEY. | 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) POST /v1/systemone wire protocol. | 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 Plus a large library (router, ONNX agent, integrations). | source 2026-10-25 |
| Which question types does it handle? | Jev's three: noul, choice, score Also a schema-driven decide() helper on top. | 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? | 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.) | stands apart it trains models, but not on Jev's outputs README describes RLCD training on datasets; one eval set is 'teacher'-labelled with the teacher unnamed. Not verified beyond the README. | 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? | yes, head-to-head numbers against Jev Publishes 'where Laya leads' and 'where Jev leads' tables. | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/NandhaKishorM/laya · read 2026-10-25
- Package registry · pypi.org/project/laya/ · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.