laya vs strands-decider
Non-autoregressive decision engine: typed choice, score and yes/no answers over text in one forward pass (~33 ms), 100+ languages, calibrated probabilities, a router picking the checkpoint. — versus — Strands' small decision model (2B, Qwen3.5-based): pick between options, answer yes/no or rate on a scale with calibrated confidence. CLI and /v1/systemone server on CUDA, MPS, MLX or CPU.
Both are open, local decision models answering typed choice/score/yes-no questions with calibrated probabilities; Laya is non-autoregressive and multilingual, strands-decider a 2B Qwen3.5 model tied to the Strands ecosystem.
| laya | strands-decider | |
|---|---|---|
| Stars | 32k | 579 |
| Forks | 2.8k | 77 |
| Language | Python | Python |
| License | Apache-2.0 | Apache-2.0 |
| Last activity | 4 days ago | 2 days ago |
| Topics | decision-models, local | decision-models, local |
| Curated connections | 8 | 5 |
laya — the curator's take
Use laya where you now spend an LLM call on a classification: routing a ticket, scoring urgency, a yes/no guard. Typed questions in, calibrated probabilities out, in one pass of about 33 ms, in 100+ languages, with pip install and extras for LangGraph, LlamaIndex, CrewAI, MCP and an HTTP server. The probabilities are the point: you can threshold them. Mind the limits it publishes itself: the multilingual checkpoint cuts at 1,024 tokens unless you pass max_len=8192, and past about 4,000 tokens its own long-document bench drops to 8 to 17 correct of 20. It decides; it does not explain or extract, so free-form answers still need an LLM. Two weeks old despite the star count: pin the version.
strands-decider — the curator's take
Use it for the many small judgments inside an agent workflow — routing, triage, urgency, sentiment — where an LLM call is too slow and training a classifier too much work; answers at ≥0.9 confidence were right ~95% of the time on unseen tasks, so threshold and escalate the rest. It decides, never writes. At 2B it runs on a laptop; for agent-action ranking at scale, CLM's cached-embedding design is faster.