All decision model projects

Video talk by TypeSafe founder Diogo Almeida on why Jev needed a separate company: a design rationale for System One models.

Arcturus Labs analysis arguing OpenAI is best placed to fast-follow Jev's typed-decision shape, with a large HN debate on moats.

Community post reporting that TypeSafe's official X account was phished on Jev's release day.

ibl.ai article noting CriticGPT and Prometheus 2 built judge models in 2024, cited as prior art for Jev's design.

Pat McGuinness Substack post on Jev making fast, cheap decisions, quoting founder Diogo Almeida on its original motivation.

James Cruce's write-up on choosing local LAYA over hosted Jev: the 421M open model beat a home-made router on a frozen replay.

Wavect's independent review of Jev, whose four caveats a directory maintainer adopted into its IO contract section S8.

HarnessRouter blog post explaining what a System One model is, noted by a curator for consistent terminology.

TechStock2 article noting that TypeSafe's headline Jev cost and performance claims, such as 445x cheaper, are self-tested.

Press coverage of Aurora Mobile's GPTBots.ai integrating Jev in a two-layer AI architecture, the first public-company integration.

classifier.dev: free zero-shot classification HTTP service built on Jev, with no API key or account and an agent skill.

Browser Texas Hold'em where a Jev bot gets structured hand state and picks a complete legal move and bet size from typed options.

Code-review CLI that coding agents run after every change, using Jev to check the diff near-instantly instead of an LLM reviewer.

Boring Tools Kit's technical SEO audit cost study, where Jev ranks striking-distance fixes and content gaps by calibrated probability.

ChemIllusion post on Jev ranking RDKit-validated structure candidates as autocomplete cards in a chemistry sketcher, about 0.2 s each.

3D browser chess where Jev plays both sides, or you take one.

X client with Jev-powered smart rules that filter the timeline by usefulness, post type and topic.

Independent multilingual guide site covering Choice, Score, Noul, Python SDK requests, thresholds, fallbacks and human escalation.

Simulated mouse colony whose behaviour is driven by Jev decisions on top of a deterministic engine.

Directory site of Jev use cases with source-code analysis and visual explanations of what Jev decides in each project.

Independent website with guides and small tools for learning to build typed Jev decision workflows.

Growth tool that asks Jev to score experiment results against a promotion bar and choose the next SEO, content or ad play.

Semantic mapping site that places phrases in 2D using Jev's scores for how strongly each relates to two chosen axis concepts.

Free browser game about surviving five awkward conversations, listed among Jev-powered games.

Unsloth desktop app docs page: serves LAYA and Clef decision models locally through a TypeSafe-compatible /v1/systemone API.

OpenRouter cookbook: Jev checks a cheap model's draft against grounding constraints before accepting it or escalating to a stronger model.

Viorant's hosted MCP service exposing Jev Noul, Choice and Score decisions to agents, with a free credit tier.

TypeSafe AI's official X account, posting product and research updates on Jev.

Post reporting the treg team runs Jev in production for traffic classification, onboarding and reranked search.

DuckDB extension that labels rows in CSV, Parquet or DuckDB tables with Jev, reported at about ten seconds per thousand rows.