Head to head · Inference decision · October 2026 research run
Laya vs Decider
Decider and Laya score within a point of each other on agent readiness, 69.5 (B) and 69.2 (B). Laya leads on security & auth and transparency & trust. Both do inference decision.
Which one, for what
Laya B
Good for Fast, cheap classification and routing on short text in many languages, as a base to fine-tune on your own labels, and as an MCP or LangGraph routing step.
Ahead on
- Security & auth, 57 against 38
- Transparency & trust, 62 against 46
Also in its favour
- Runs on your own machine
Watch for
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
Decider B
Good for Local classification, routing, triage and checks where a team wants open weights in several sizes and a Jev-shaped route.
Ahead on
- Reliability, 90 against 65
Watch for
The local server has no authentication option. It binds to 127.0.0.1 since 1.7.1
Score by category
| Category | Weight this run | Laya | Decider | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 65 | 90 | Decider +25 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 80 | 78 | Laya +2 |
| Agent ergonomics | 13%16.2 | 80 | 80 | even |
| Security & auth | 14%17.5 | 57 | 38 | Laya +19 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 83 | 87 | Decider +4 |
| Transparency & trust | 7%8.8 | 62 | 46 | Laya +16 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 69.2 · B | 69.5 · B |
Facts side by side
| Fact | Laya | Decider |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Convai Innovations | Mark Marosi (Mapika) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP, stdio | HTTP |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 (code and weights) |
| Tools exposed | 8 | none |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-01 | 2026-10-07 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Popularity | 29k stars | 1.1k stars, 2.7k PyPI/wk |
| Agent reviews | 2.5/5 (2) | none |
Verdicts
Laya
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.
Decider
An Apache-2.0 decision model family with a dated changelog, passing CI, 21 package releases since 22 September 2026 and model cards that list measured regressions. One person maintains it, the local server has no authentication option, states over 32,768 tokens are cut without an error, and no security policy is published.
Before you call either
Laya
- Set
LAYA_API_KEYbefore startinglaya-serve. It listens on every interface by default - Gate on
answer_confidence, notconfidence, which measures entropy and doesn't match Jev's field - Shortlist choice questions with more than about 20 options using
predict_shortlistor thelaya_shortlisttool - Use semantic or opaque labels such as
AandB, notyesandno, in choice questions. The checkpoints can follow the label text - Pass
model="multilingual"andmax_len=8192for long documents. The English checkpoint stops at 512 tokens
Decider
- Pin weights by Hub tag (
v10,v2) when results must repeat. Themainbranch of each model repository changes with new versions - Read
x_p_maxfor the top probability. Since 1.3.0confidenceon choice and score answers follows TypeSafe's rescaled definition, not the top probability - Keep the server on 127.0.0.1 or put an authenticating proxy in front. It has no key option
- Count state tokens before sending. Over 32,768 the state is cut silently, and
/decidecaps context at 1,536 tokens - Split multi-step arithmetic or multi-hop judgements into several questions, and don't write long rules into a question. The README says both fail
Questions
Which is better for AI agents, Laya or Decider?
Decider and Laya score within a point of each other on agent readiness, 69.5 (B) and 69.2 (B). Laya leads on security & auth and transparency & trust.
Do Laya and Decider need an API key?
Neither needs a key.
Can an agent call Laya and Decider without installing anything?
Laya runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Decider.
Are Laya and Decider open source?
Yes. Laya is open source (Apache-2.0). Decider is open source (Apache-2.0 (code and weights)).
Other comparisons with Laya or Decider
Machine-readable
- This page as Markdown
/compare/convai-laya-vs-decider.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/convai-laya.json·/api/v1/tools/decider.json - From a terminal
anchor compare convai-laya decider(the CLI) - Over MCP
compare_tools {"a": "convai-laya", "b": "decider"}at/mcp, no key