145 curated Jev entries. Framework, platform, gateway, and database integrations that put Jev inside the stack you already run, from LangChain and Pydantic AI to Postgres and Home Assistant.
By format
Docs2
Repos & sites142
Articles1
All 145 Jev Integrations & Adapters
Search the full category, or filter by format and tag.
Ruby gem that models Jev as field predicates: feels and decide bind to model attributes with shared definitions, thresholds, confidence gates, batching, and test tapes.
Experimental language where questions and methods are composable values, with standalone .jpp sources run by a native Rust kernel and a Python implementation kept as reference.
Compiler that turns ignored markdown rules into testable Jev gates: typed questions answered with probabilities plus a reducer computing allow, ask, or deny in code. Ships with offline replay fixtures and Claude Code hook wiring.
Community Agent Zero plugin that exposes one typesafe_query tool for combined Choice, Noul, and Score questions over the same evidence, with probability cards in chat.
Shadcn registry search block that shows lexical hits instantly then re-ranks the top candidates with Jev intent scoring in one request, with keyword fallback on failure.
Native C++ DuckDB extension that runs Noul, Choice, Score, and mixed judgments directly from SQL with batching, concurrent HTTP, and chunked streaming and no Python UDFs.
Experimental OpenTelemetry Collector processor that asks Jev about metric metadata and applies explicit keep or drop policy, starting in annotate mode.
Unofficial community component workspace for TypeSafe AI projects: a Turborepo and pnpm monorepo with a Next.js component browser, shiki-highlighted source previews and an interactive Lab, built on shadcn base-nova, Base UI primitives, Tailwind v4 and RTL-aware components.
React library on npm where Jev judgments choose presentation: `Branch` picks a subtree, `Rank` orders or truncates a candidate set, `Gate` shows an affordance, and `useScore` returns a number you can use as an ordinary prop.
Task plugin that puts TypeSafe's System One endpoint behind a QuantumNous/new-api channel, so clients keep posting `/v1/systemone` while new-api handles auth, routing, model mapping and token billing against either TypeSafe or the Vercel AI Gateway.
TypeScript guardrail that puts seven Jev checks in front of an AI SDK model or an OpenAI-compatible endpoint, blocks on high-confidence hard checks, downgrades low confidence to a flag, and logs every verdict as a PII-free JSONL row you can turn into an eval set.
MCP layer that lets an agent harness ask Jev for a bounded choice from a candidate set it already allows, while permissions and execution stay with the host.
A GitHub Action that labels new issues only when the label probability and the model's own confidence both clear thresholds you set, and otherwise leaves the issue untouched and says why.
Symfony app that streams a public French support-request dataset into SQLite and qualifies each request in background batches: Choice for intent, Score for urgency, Noul for whether it is a bug to forward.
n8n community node that asks Jev several independent questions about the same state in one execution, returning typed probabilities for choice, yes/no and rubric scoring questions.
An n8n community node that classifies, scores and checks text with Jev, shaped like the built-in Text Classifier with one output branch per category plus a Needs Review branch, and built for volume with parallel requests and packed batches.
Four small Pydantic AI demos that put a Jev question at a fixed hook, before the model runs, before a tool runs or after the run ends, and act on the number.
A Letta agent skill that wraps TypeSafe System One (Jev) as a cheap external judge for texts and decisions, plus a paragraph scanner that maps where a document argues, lists, asks, or admits uncertainty. The README is in Russian.
A Next.js workbench that converts OpenAI-compatible Chat Completions requests into Jev state and typed questions, compares chat output against structured judgments, and publishes saved question packs as proxy routes. The interface is mainly in Chinese.
A Home Assistant Assist conversation agent that sends each command to Jev as one request with a speculative fan-out of questions, then hands the typed answers to Home Assistant's own intents to do the device control.
Python library that maps Jev's Choice, Score and Noul onto verbs like classify, score, check, where, extract, verify and rank, keeping data shape in and out, batching one request per distinct row and caching answers.
TypeScript build of hunch for Node 20 and up, mapping Jev's Choice, Score and Noul onto classify, score, check, where, extract, verify, rank and route over arrays and row objects.
Neovim popup that reads the verdict jev-lens writes after a Claude Code edit and tells you whether to open a diff, which files matter and why, with a strip-debris action, lazydiff on a key, and no API calls of its own.
Tiltmeter records the probabilities Jev returns for every question your app asks and alerts when one moves: a version change behind jev-latest, drift away from baseline, too many answers sitting next to your threshold, or an estimated accuracy drop computed without labels.
A Jev-protocol model gateway: a Rust and axum daemon turns an editable routing DAG into the actual call path, with a React console, a Tauri desktop shell and a Docker image.
n8n community node for TypeSafe's System One API, exposing yes or no, choice and score questions as workflow nodes, with an Evaluate Questions operation that batches several over one state in a single request.
A Choice-only decision framework around Jev: a local rule engine answers reject, short-circuit, route and constrain cases with no remote call, and only misses reach a Choice request on TypeSafe, Cloudflare, Vercel or a self-hosted host.
Fifteen independent local plugins for the Paseo desktop app, two of which use Jev: an evaluator exposed to Codex and Claude agents over MCP, and an orchestrator that routes a task to one model profile and effort level.
An OpenClaw plugin that registers a single optional tool, typesafe_decide, forwarding caller-supplied text or JSON state plus typed noul, choice and score questions to the System One endpoint, with jev-latest as the default model.
Python adapter that puts Jev's Noul, Choice and Score checks inside Mellea generation flows: verify a requirement, classify text into caller-defined categories, or rate it on an ordered scale, each attachable as a Mellea Requirement.
An alpha Python library that uses Jev to grade model responses for hallucination, correctness and instruction following, returning Noul probabilities and five-level severity Scores.
ACP stdio agent that evaluates explicit Choice, Score and Noul questions as typed Jev answers inside any Agent Client Protocol client or IDE, driven by a task picker rather than free-form chat.
Unreleased Rails engine that turns Ruby-defined commands into voice and typed shortcuts, using Jev to interpret free-form phrasing while your own authorize callbacks keep the permission decision.
Alpha OpenTelemetry Collector processor that scores operation metadata with three Jev noul questions, caches the result, and writes it onto later matching spans as jevtraces.operation annotations.
The official Laravel AI SDK: one interface across providers such as OpenAI, Anthropic, and Gemini, covering agents with tools and structured output, image generation, audio, and embeddings.
A section-by-section guide to agent harnesses - loop, tool runtime, permissions, hooks, subagents, skills, memory, background work - using Claude Code, mini-swe-agent, Hermes Agent, and deepseek-harness as worked examples.
A Python speech-to-speech avatar framework: swappable VAD, STT, LLM, and TTS modules behind one streaming pipeline, with WebSocket, telephony, LINE, and OpenAI-compatible channel adapters on top.
Smithers turns issues into reviewed, tested changes through flows defined beside your code, with an optional step that keeps the project wiki current. The 1.0 release candidate runs from a source checkout.
A self-hostable API server that fronts text, vision and data endpoints across Ollama, LM Studio, LlamaCpp and a long list of hosted providers, and also runs tool-using agents with sessions. Jev appears separately as a decision provider for typed choice, score and noul questions.
The model-integration layer for the Milvus vector database, shipping adapters for embedding and reranker models from hosted providers, Jev among them, plus local backends.
Elixir library for agents, graph workflows and deep agents, built on OTP supervision with Ecto and ETS boundaries plus adapters and tracing instead of a Python runtime.