What is Strands Decider?

A small, fast decision model — what the README calls a system one model — for agentic workflows. Instead of generating text, it picks between sets of options or rates things on a scale, with a confidence on every decision.

Is Strands Decider the same thing as Jev?

No. It belongs to the same class of decision or system one models as TypeSafe's Jev, and its README describes the class rather than Jev itself. It ships from Strands Labs and does not call Jev.

What can I ask Strands Decider?

Short classification questions with options, like whether a word contains three r's or which language a phrase is in, and rating questions such as how positive a sentence is between 0 and 1.

How reliable are its confidence scores?

The evaluation summary says answers at a confidence of 0.9 or more on unseen short classification tasks are right about 95% of the time; below that, the README advises confirming or asking a person.

How do I install Strands Decider?

The fastest route is the strands-decider CLI installed with pip install strands-decider. The README then starts an Apple-silicon section that the digest truncates, so further setup steps are not available.

Does Strands Decider cost anything or need an API key?

The repo is Apache-2.0 licensed and the digest shows no hosted API, pricing, or key requirement — the CLI installs as a Python package. Whether it downloads weights or runs fully offline is not stated in the excerpt.

Who builds Strands Decider and how active is it?

strands-labs, the group behind the Strands Agents SDK, whose Python repo the README links. Metadata: 660 stars, 89 forks, created 2026-09-29, pushed 2026-10-16, with a Discord community linked.

Jev directory

CommunityJev Models & Reimplementations

Strands Decider

A small, fast decision model — a system one model — for agentic workflows from Strands Labs: it picks between options or rates on a scale faster than an LLM and returns a calibrated confidence with every decision.

See highlights Open github.com

Stars: 664
Language: Python
License: APACHE-2.0
Reading time: 2 min
Published by: Community
Author: strands-labs
Last verified: Oct 2026

strands-labs/strands-decider

Organization repository on GitHub

View on GitHub

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.

Forks: 89
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

Tagscommunity github python decision-model agents

Works forJev for Classification Jev for Scoring Jev for Decision gating

Used inJev for Software & DevTools

Languages: Python
Platforms: CLI
Capabilities: Open sourceRuns locally

Highlights

Picks from options or rates on a scale: examples include identifying a language and scoring positivity between 0 and 1.
Calibration from evaluation/results.md: on unseen short classification, answers at 0.9+ confidence are right about 95% of the time.
Positioned between LLMs and traditional classifiers; a natural fit for decisions inside Strands Agents SDK workflows.
Install with pip install strands-decider; the README's Getting Started section mentions an Apple-silicon setup.
GitHub: 660 stars, 89 forks, Apache-2.0, created 2026-09-29, last pushed 2026-10-16; a Discord invite is linked.

Quickstart

bash

pip install strands-decider

Watch out

README reviewed 2026-10-17 and truncated just after Getting Started begins, so full CLI instructions, hardware requirements, and model download details are unavailable in the digest. The 95% figure is the project's own evaluation on short classification tasks; this is not TypeSafe's Jev but a peer decision model.

Questions about this entry

Short answers drawn from the linked project or page.

From the Jev guides

Original write-ups on what this entry is for.

Beyond text and boxes: multimodal decisions you can run yourself

Oct 16, 2026

Jev-Omni's merged classifier scores text, image, audio, and video options; VideoJev and Laya Vision show what open multimodal decision models accept, what they return, and which numbers are the authors' own.

Jev Models & Reimplementations#multimodal#open-models#vision

Read article

Jev 1.14: Images, Box, and the Danger Zone

Oct 15, 2026

Jev Day shipped a routine model bump and a deliberate widening of the API: images on both models, a box question type on 1.14 only, and 262k context, all behind danger-zone headers.

Jev Models & Reimplementations#release#vision#danger-zone

Read article

The Open Decision-Model Roundup

Oct 14, 2026

Training recipes, looped architectures, and language ports: what the open side of the typed-decision class shipped this month, and how to pick by runtime and calibration instead of the leaderboard.

Jev Models & Reimplementations#open-models#training#local

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Strands Decider

Highlights

Quickstart

Questions about this entry

What is Strands Decider?

Is Strands Decider the same thing as Jev?

What can I ask Strands Decider?

How reliable are its confidence scores?

How do I install Strands Decider?

Does Strands Decider cost anything or need an API key?

Who builds Strands Decider and how active is it?

More Jev resources like this

From the Jev guides

From the Jev AI model community