What is Awesome Open System One?

A curated list of the open side of the System One ecosystem: runnable reproductions of Jev-like decision models, independent benchmarks, and the calibration and constrained-decoding tooling that makes typed, confidence-aware decisions work.

How is it different from other awesome-jev lists?

It is deliberately about what you can run and audit yourself, not what uses the closed hosted Jev. The README points readers to the other awesome-jev lists for projects built on the hosted TypeSafe model.

What counts as a System One model in this list?

The introduction defines it as a model that takes a block of state plus a set of typed questions and returns one typed answer per question with a calibrated confidence in a single parallel pass, with output schema-valid by construction rather than generated text.

Which projects does the list feature?

The visible section includes poorjev (provably calibrated confidence, measured ECE 0.170 to 0.071), von (sub-15 ms non-autoregressive), Laya (421M, RLCD-trained probabilities), NanoJev, kev, SemIf, laya-mlx, simple-jev, OpenThai-SystemOne and jevos.

Does the list also cover benchmarks and decoding?

The contents include dedicated sections for independent benchmarks and evaluations, calibration and selective prediction, and constrained and structured decoding. The digest copy is truncated before their entries, so this entry does not enumerate what those sections contain.

Is every listed project open?

The README states all links are verified and every entry is open source or openly readable. GitHub metadata for the list repository itself reports NOASSERTION rather than a named licence, so check each linked project's own licence before adopting it.

Who maintains the list?

rupeshpoojary9 maintains the repository, created 20 September 2026 and pushed 4 October 2026, with topics covering awesome lists, calibration, conformal prediction, constrained decoding, structured output, llm and System One.

Jev directory

CommunityJev Guides & Articles

Awesome Open System One

A curated list tracking the open side of the System One ecosystem — runnable Jev-like models, independent benchmarks, and calibration and constrained-decoding tooling — as the counterpoint to lists about the closed hosted Jev.

See highlights Open github.com

Stars: 9
Reading time: 2 min
Published by: Community
Author: rupeshpoojary9
Last verified: Oct 2026

rupeshpoojary9/awesome-open-system-one

User repository on GitHub

View on GitHub

Curated list of the open System One ecosystem: open models, independent benchmarks, calibration and constrained-decoding tooling.

Forks: 6
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

Tagscommunity catalog-import cobanov awesome-list calibration open-models

Works forJev for Evaluation

Used inJev for Software & DevTools

Capabilities: Open source

Highlights

Sections cover open models and reproductions, independent benchmarks, calibration and selective prediction, constrained decoding, and reference reading.
Lists entries such as poorjev (measured ECE 0.170 to 0.071), von (sub-15 ms non-autoregressive), Laya, NanoJev, kev, SemIf, laya-mlx, simple-jev and jevos.
Deliberately excludes projects that merely use the closed hosted Jev, pointing readers to other awesome-jev lists for those.
States every link is verified and every entry is open source or openly readable.

Watch out

Copy reviewed against the repo README on 2026-10-15; the pasted README was truncated mid-way through the open-models list, so later sections are described from their headings only. GitHub metadata reports the licence as NOASSERTION rather than a named licence.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: Standard One SH (StandardThinking)

LinkedIn: What multimodal decision models actually change, and what they do not.

LinkedInJevDirectory.org

Hacker News: Decision Index 0.2.1 scores open reproductions of Jev on a frozen suite.

jackbravo4 pointsDecision Index 0.2.1 – 70 open reproductions of TypeSafe Jev's Decision ModelRead the thread on Hacker News

Hacker News: Pointer to a DiffusionGemma plus vLLM tutorial for a Jev-shaped classifier.

1 pointHow to build a Jev-style classifier with DiffusionGemma and vLLMRead the thread on Hacker News

From the Jev guides

Original write-ups on what this entry is for.

The trust ledger: measuring confidence your domain has earned

Oct 16, 2026

ASSAY-001 calibrated Jev on CLINC150 but found it overconfident on Banking77 — one audit, two verdicts. How calibration research measures the model-and-domain pair, discounts stated confidence, and signs the evidence.

Jev Benchmarks & Evaluations#calibration#evaluation#open-models

Read article

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

Fine-Tuning and Calibration: Making an Open Checkpoint Yours

Oct 9, 2026

Base decision checkpoints sit near chance on purpose. The typed-decisions loop, the corpora behind the students, and the temperature fit that turns probabilities into thresholds.

Jev Practices & Patterns#fine-tuning#calibration#open-models

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Awesome Open System One

Highlights

Questions about this entry

What is Awesome Open System One?

How is it different from other awesome-jev lists?

What counts as a System One model in this list?

Which projects does the list feature?

Does the list also cover benchmarks and decoding?

Is every listed project open?

Who maintains the list?

Reactions & coverage

Related terms

More Jev resources like this

From the Jev guides

From the Jev AI model community