strands-decider social preview
agent-framework1,240Apache 2.0

strands-decider

A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confide…

Updated Nov 21, 2026
Platforms
macos
Pricing
free-open-source
Status
active
License
Apache 2.0

What it does

Core capabilities at a glance

  • Natural Language Understanding
  • Strands Agents
  • Strands Labs
  • System ONE
  • System ONE Models

Deep dive

The full breakdown - performance, comparisons, and setup

strands-deciderLink to this section

strands-decider is an agent framework - A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confidence on every decision.

OverviewLink to this section

Strands decider is one of a new class of decision models, or "system one" models. Unlike an LLM, which can generate arbitrary text, a decision model picks between sets of options and rates things on a scale. This class of model works best for problems that fall between LLMs and traditional classification models: it is a general-purpose classification and scoring model that responds faster than an LLM and does not take the time and expertise to train that a traditional classifier does. That makes it a natural fit for the decisions inside agentic workflows built with the Strands Agents SDK.

  • Pick from options — "Are there three r's in strawberry? Yes or no." "What language is the phrase 'sihamba ngokushesha' in? English, Zulu, or Dutch." - Rate on a scale — "How positive is 'this is the best doc I've ever read'? Between 0 and 1." - Calibrated reliability scores — every decision carries a confidence. On short classification tasks it has never seen, answers at a confidence of 0.9 or more are right about 95% of the time (evaluation/results.md); below that, confirm or ask a person. Frontier LLM inference APIs do not expose anything equivalent.

strands-decider is open-source, written primarily in Python, with 1,240 GitHub stars under the Apache 2.0 license. The latest release is v0.3.0 (2026-11-05).

Key capabilitiesLink to this section

From the project's documentation:

  • Pick from options — "Are there three r's in strawberry? Yes or no." "What language is
  • Rate on a scale — "How positive is 'this is the best doc I've ever read'? Between 0 and 1."
  • Calibrated reliability scores — every decision carries a confidence. On short
  • is the size of the base model, as its Hugging Face id writes it (2B, E4B).
  • is the base model family (qwen3.5, gemma4).
  • v counts the releases on one base family: v1 is the first release on each base.

InstallLink to this section

A quick way to get started (always check the official docs for the latest):

pip install strands-decider

How it fits a local-AI stackLink to this section

strands-decider runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:

SourcesLink to this section

Stats from GitHub, 2026-11-19.

From the community

What users are saying

“You're (understandably) a bit mixed up here. Strands Agents is an agent SDK. Strands Decider is a decision model.”

“This is a great model. I've been running it on device in chrome extension to filter things like email. It is just the right mix of size, capability and speed to make it generally useful for adhoc bulk classification tasks. For those wanting to run it in browser: https://huggingface.co/alxnahas/strands-decider-2B-webgpu”

“Strands decider actually uses a small cheap/free Chinese model for its base architecture: Qwen”

Frequently asked

Quick answers to common questions

What is strands-decider?

strands-decider is a agent-framework tool for local AI workloads. A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confide…

Is strands-decider free and open source?

Yes, strands-decider has 1,240 GitHub stars and is licensed under Apache 2.0. You can self-host it for free on macos.

What platforms does strands-decider support?

strands-decider runs on macos.

What hardware do I need for strands-decider?

The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. strands-decider has 1,240 GitHub stars and an active community.

Does strands-decider support GPU acceleration?

strands-decider supports GPU acceleration via CUDA, Metal, or Vulkan depending on your platform. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.

What are the best alternatives to strands-decider?

Popular alternatives include other agent-framework tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.

How much does strands-decider cost?

strands-decider is free-open-source. It is completely free and open source to self-host.

Pairs well with

Complementary tools, models, and hardware