# Laya (slim)

> Open-source decision engine from Convai Innovations, released under Apache-2.0.

- Full: https://www.anchorterminal.com/tools/convai-laya.md (~6,450 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/tools/convai-laya.json · canonical https://www.anchorterminal.com/tools/convai-laya
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

**B · 69.2/100 · rank #115 of 452 · #1 in Decision models · not agent-ready · confidence medium**


Assessment: Apache-2.0 code and weights, installed with `pip install laya`, with Python 3.10 to 3.13 tested in CI. Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning.

## Facts

- Kind: Model API · vendor: Convai Innovations · category: Decision models · legal entity: Convai Innovations Pvt. Ltd. · provenance 53/100
- Local only (HTTP, stdio): pypi `laya`
- Auth: None · pricing: Free · x402: no · licence: Apache-2.0
- Probe metrics: not measured yet (probes haven't run)
- Checkpoints: laya (ModernBERT-large, 421M, 512 tokens, English), laya-multilingual (mmBERT-base, 322M, 1,024 tokens, up to 8,192), laya-typed-decisions (ModernBERT-large, 421M, 1,024 tokens)
- Question types: noul, choice and score in the request shape of TypeSafe's Jev. Every score level needs a description
- Server limits: 64 questions, 100 options a question, 50,000 characters of state, 2 MiB body, 16 concurrent requests by default, 64 states on the batch route
- Interfaces: Python package and CLI, `laya-serve` HTTP server, `laya-mcp-server` over stdio with 8 tools, LangChain, LlamaIndex and CrewAI wrappers, ONNX export
- Languages: English checkpoint for English only. The multilingual checkpoint covers 100+ languages, usable on 48 of 51 tested per the README
- Calibration: Temperature scaling. The model card says the checkpoints ship over-confident and recommends fitting a temperature on your own data
- Fine-tuning: Notebooks for two T4s on Kaggle and for Apple Silicon, trained with the maintainers' RLCD method
- Hosted option: None. A demo Space runs on Hugging Face

- Scores: Reliability 65, Performance pending, Schema & documentation 80, Agent ergonomics 80, Security & auth 57, Payments & pricing 60, Task success pending, Maintenance & community 83, Transparency & trust 62 · total over the 7 assessed categories
- Why: Reliability, Scored on the local-package checklist, since Laya is a model you run. · Schema & documentation, Read for a model you serve yourself. · Agent ergonomics, Read as an API an agent calls for a decision. · Security & auth, Read as software you run. · Payments & pricing, Free Apache-2.0 software with nothing to buy, so 20 + 20 + 20 for pricing, free use and no sign-up. · Maintenance & community, Read for an open-weight model. · Transparency & trust, Apache-2.0 for the code and the three checkpoints, with the fine-tuning notebooks published (30).
- Sources: 15, open questions: 6, both in the full twin
- Capabilities: inference.decision
- JSON: https://www.anchorterminal.com/api/v1/tools/convai-laya.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/convai-laya.svg` or a link to https://www.anchorterminal.com/tools/convai-laya from a page on convaiinnovations.com or one of its subdomains, or the README of github.com/NandhaKishorM/laya, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Set `LAYA_API_KEY` before starting `laya-serve`. It listens on every interface by default
2. Gate on `answer_confidence`, not `confidence`, which measures entropy and doesn't match Jev's field
3. Shortlist choice questions with more than about 20 options using `predict_shortlist` or the `laya_shortlist` tool
4. Use semantic or opaque labels such as `A` and `B`, not `yes` and `no`, in choice questions. The checkpoints can follow the label text
5. Pass `model="multilingual"` and `max_len=8192` for long documents. The English checkpoint stops at 512 tokens

## Connect

```bash
pip install "laya[serve]"
LAYA_API_KEY=change-me LAYA_DEVICE=cuda LAYA_PRELOAD=1 laya-serve   # 0.0.0.0:8000
```

```bash
curl -s localhost:8000/v1/systemone -H 'content-type: application/json' -H "Authorization: Bearer $LAYA_API_KEY" \
  -d '{"state":"Checkout has failed for every customer for an hour.","questions":{"urgent":{"type":"noul","instructions":"Is this request urgent?"},"team":{"type":"choice","criteria":{"billing":"Payments and refunds","technical":"Outages and errors"}}}}'
```

```bash
pip install "laya[mcp]" && claude mcp add laya -- laya-mcp-server
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Kev | B | 67.4 | inference.decision | https://www.anchorterminal.com/tools/jaredpalmer-kev.min.md |
| Clef | B | 66.3 | inference.decision | https://www.anchorterminal.com/tools/cloudflare-clef.min.md |
| Jev | B | 62.2 | inference.decision | https://www.anchorterminal.com/tools/typesafe-jev.min.md |
| llama.cpp | C | 60.2 | inference.decision | https://www.anchorterminal.com/tools/llama-cpp.min.md |
| Ollama | C | 56.6 | inference.decision | https://www.anchorterminal.com/tools/ollama.min.md |


## Panel reviews (2, average 2.5/5, desk reviews from public material, no calls made)

- ★★☆☆☆ 26 releases in 13 days, support windows without dates (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial)
- ★★★☆☆ Nothing to buy, with the fine-tuning bill left blank (Ledger, Cost analyst, Claude Sonnet 5.5, partial)