Jev Libraries and Framework Integrations

Parcha-ai/agentrun

A workflow DSL for agents with a Jev package for the steps that are decisions rather than generation.

osolmaz/switch

TypeScript framework for decision-model harnesses: your program offers a short list of next steps and the model picks one at a time until it can answer, with chess, wikirace and rubric-judge examples run on Jev.

disler/ten-levels-of-jev

Thirty worked uses arranged in ten levels, from one if statement to an agent that reaches for Jev itself, with a video walkthrough.

libingzheren/Jev-Mem

Memory layer for long-running agents that routes the frequent memory-management decisions to Jev and leaves the deeper reasoning to the LLM. Comes with a paper.

HarnessRouter/SystemOneHarness

Turns a decision model into an agent loop: it compiles the environment's finite action space into typed questions, gates each step by confidence, and records the trace.

peterfriese/system-one-foundation-models

Swift 6 bridge that puts Jev behind Apple's Foundation Models framework, with ticket- and mail-triage example apps.

pithings/advocaat

Small type-safe TypeScript client for asking Jev about your data, with an agent skill for designing questions.

AboveColin/HA-Jev

Home Assistant integration that turns Jev's answers about your house into entities.

hyperspaceai/jevcache

Local decision cache keyed on (model, schema, state), with redaction and canonicalisation before hashing, for cheaper repeats and deterministic replay in CI. No license file at the time of writing.

iamaamir/system-one

Provider-neutral TypeScript runtime for typed decisions: the same call runs against Jev, a local implementation, or any /v1/systemone endpoint. No licence file.

tomerglick57/Jevstiller

Sits in front of a repeated classification call, trains a local model on Jev's own answers and their distributions, checks the two agree within a budget you set, and then answers most requests itself.

chigwell/typesafe.pro

The full server behind api.typesafe.pro, a free anonymous front door that speaks Jev's request shape and forwards to TypeSafe on the operator's own key. AGPL-3.0, so you can run it yourself.

obie/feelings

Probabilistic conditionals for Ruby, Feelings(message).like?("genuinely urgent"), answered by a decision model through ruby_decision_model, with descriptions and label sets in YAML.

yusukebe/hono-jev-router

Experimental Hono router that matches requests against plain-language descriptions instead of paths.

kieranklaassen/truffler

Intent search for Rails: the typed questions you declare about a record are asked when it is saved and the answers stored, so the query at read time is ordinary SQL.

jlowin/vibecheck

Drops a decision model into ordinary Python code, so a judgement call is a function call rather than a prompt.

cmpnd-ai/dspy-system-one-agent-patterns

Six files, one coding agent, one pattern each, on a single rule: the signature states the question, Jev returns the probability, and plain Python owns the policy.

nexibeo/jev-cookbook

Fifteen runnable recipes calling Jev through OpenRouter - support triage, dedupe, PII column scanning, reranking, moderation and more - each shipping the output it produced beside it.

TypeLLM/pijev

Drop-in wrapper for the official Python SDK that asks each question in several option orders and averages the answers, so a decision does not move when the options are shuffled.

Towow-ai/jpp

Experimental language in which a question is a value and methods compose them, with a Python foundation and a Rust runtime, both speaking /v1/systemone. Every demo replays a recorded run and says what is unsettled. Chinese and English.

Jev-Engineering/cookbook

Planned set of sixty notebook recipes for Choice, Noul and Score patterns, 33 published so far, each runnable offline on fixtures and labelled with the mode it ran in.

TypeSafeAI/typesafe-playground

Community playground with 110 use cases, A/B input comparison, editable prompts, and games built on typed answers. From the independent TypeSafeAI community organisation, not the official team.

ItIsCuthNotCup/MetaCog

Wraps a language model in a metacognition loop where a System One judge, Jev or the open Reflex model, picks which branch of reasoning continues.

BoundaryML/feelings

BAML language support for an AI if-statement: .feels() as a real, typed method backed by a decision model.

agencyenterprise/jev-recipes

Two hundred small decisions as installable TypeScript, each a typed question with its options, for routing, grading, gating, comparing and labelling.

chopratejas/invalidate

Gives every remembered fact a lease and asks Jev whether new evidence ends it, so an agent's memory can be made to go stale on purpose.

hraness/algal

A language and VM for agent programs that wait for approval, resume after a crash and replay what they did, with typed decisions at the branch points.

Qew7/jev-feels

Ruby and Rails: email.feels?(:urgent) as a named question on a field, with decide and score beside it and validations that use them.

gopinav/jev-demo

Worked examples of every question type against the TypeScript SDK, written to be read in order.

carldaws/hunch

Probabilistic control flow for Ruby and Rails, with predicates that read like ordinary conditionals.

Ray-Hughes/jevalyn

Rails-native decision layer with typed results, guardrails, a router and test helpers.

kieranklaassen/ruby_llm-typesafe

TypeSafe provider for RubyLLM 2.

vinibrsl/gut

Elixir DSL that picks an Elixir value for a subject and a question, with a Jev backend among the LLM ones. On Hex.

doeixd/discern

Semantic control flow for Effect: patterns, policies and routable procedures built on typed decisions, where an uncertain answer is a branch you must handle.

Kludex/pydantic-ai-go

Go port of PydanticAI's agent loop, tools and structured output, with a TypeSafe Jev model provider and a generic System One provider alongside the LLM ones.

AntonioCoppe/jev-harness

TypeScript library that wraps Jev answers in policies, confidence gates, shadow mode, and reusable recipes.

j1s4nn/duomind

OpenAI-compatible local server that pairs a small llama.cpp model for generation with a decision model for the closed questions, so generation stays on your machine.

CharlesFeng0314/JEV_sees

Gives Jev eyes: turns an image, a video stream or an RGB-D camera into the structured state a typed question can be asked about, for risk and triage judgments over what a camera sees.

kushals256/jevcache

OpenAI-compatible proxy that asks a System One model whether a new question is the same one it has already answered, and replays the cached reply when it is. Not the same project as the jevcache above.

backant-io/jevelry

Puts Jev behind ordinary decisions across a codebase and keeps a record of each one it makes.

reachjalil/jev-tree

Recursive Choice over a taxonomy, for picking among more options than a single Choice question allows.

jomatsu/zod-jev

Adds Jev semantic checks to Zod 4 schemas. Zod validates the shape; Jev validates the meaning.

zampierid4p/n8n-nodes-typesafe

n8n community node for asking typed questions inside workflows.