JevCodeIntegrations & bridges
Wiring Jev into existing data sources and protocol stacks such as Postgres and ACP/MCP.
Projects in this category
- agentgateway/agentgatewayGitHub ↗★ 5.9kRustA Jev guardrail example in Agentgateway using a webhook to inspect model requests and responses.
- typesafe-ai/skillsGitHub ↗★ 2.9k—Agent skills for building with TypeSafe's System One API
- vellum-ai/vellum-assistantGitHub ↗★ 1.5kTypeScriptAn optional Jev provider in Vellum Assistant sends conversation state and explicit questions to TypeSafe.
- realZachi/pg-jevGitHub ↗★ 1.2kPythonAsk your Postgres tables questions in plain language — a PostgreSQL extension powered by Jev.
- kentcdodds/kodyGitHub ↗★ 887TypeScriptOptional second-stage search: widen the hybrid pool, then Score-rerank candidates with Workers AI typesafe/jev.
- AgentiLoop/AgentGitHub ↗★ 652SwiftAn optional Jev command-risk advisor inside a native macOS Agent, with a TypeSafeKit client.
- jkudish/jev-mcpGitHub ↗★ 562TypeScriptEight MCP tools for evidence checks, content screening, search, reranking, classification, comparison and extraction.
- superagents-lab/jev-searchGitHub ↗★ 550—Searches the web with Jev choosing sources and time ranges, then ranking returned links.
- dabit3/jev-experimentsGitHub ↗★ 412TypeScriptA collection of Jev developer-tool experiments, including Commit Sentry for semantic checks on staged diff hunks.
- kitze/unclutterGitHub ↗★ 387TypeScriptA browser extension using Jev to identify ads, promotions, and subscription popups and save reusable hiding rules.
- itsmostafa/typesafe-mcpGitHub ↗★ 357GoAn MCP server that lets Claude Code, Claude Desktop, Codex and Pi ask Jev typed questions.
- QuentinCody/interlinked-cliGitHub ↗★ 182—Interlinked adds optional Jev judgments and evidence checks to local coding-agent checks.
- DevMortimer/pi-wardenGitHub ↗★ 177TypeScriptAdds checks for project rules, out-of-scope actions, repeated failures, and completion claims to Pi Agents.
- y0usaf/pi-jevGitHub ↗★ 165TypeScriptA Pi extension that flags tool risks before execution and checks output for secrets and failure types.
- uehaj/jev-semgrepGitHub ↗★ 150JavaScriptA semantic grep that scores each line with Jev against a meaning, including AND/OR/NOT and cross-language queries.
- leepokai/jev-guardGitHub ↗★ 144JavaScriptTool-call checks for coding Agents that assess operation risk, user intent and prompt-injection signals.
- devagrawal09/stanley-codeGitHub ↗★ 119TypeScriptBounded TypeSafe Jev workflows for coding agents.
- AkashPriyadarshii/jev-curateGitHub ↗★ 107RustA Rust dataset-filtering experiment using Jev scores to keep or reject text records.
- pithings/advocaatGitHub ↗★ 101TypeScriptA small, type-safe client for asking AI questions about your data.
- giuliosmall/pg_typesafeGitHub ↗★ 84CA pre-alpha PostgreSQL C extension for calling Jev from SQL for classification, yes/no judgments, and scoring.
- CaptainCore/captaincoreGitHub ↗★ 76GoJev commands in the WordPress toolkit CaptainCore answer structured questions and prioritize malware scanner findings for review.
- TheoOliveira/pi-jevGitHub ↗★ 72TypeScriptHelps Pi Agents find tools and skills for a task, with structured evaluation and optional history filtering.
- shitianfang/jev-useGitHub ↗★ 64JavaScriptClaude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM
- getsynkora/synkora-aiGitHub ↗★ 55—Synkora includes optional TypeSafe client tools for classification, scoring and yes/no judgments.
- brainstormity/Jev-Moderation-BotGitHub ↗★ 50PythonA Discord moderation bot using Jev to check spam and scam links, with local warning and timeout rules.
- DevMortimer/pi-typesafeGitHub ↗★ 48TypeScriptA Pi Jev extension providing a decision tool, terminal playground commands and an API for other extensions.
- gamesonrblx/JevbridgeGitHub ↗★ 47TypeScriptACP and MCP adapter bridging Jev with any LLM — typed decisions alongside Codex, Claude, Grok, and OpenCode.
- tacticocc/JevbridgeGitHub ↗★ 47TypeScriptACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
- dannote/jevGitHub ↗★ 37ElixirTypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer
- jomatsu/pi-jev-auto-modeGitHub ↗★ 33TypeScriptAdds rule checks to Pi commands and file operations, then uses Jev to assess cases that need further judgment.
- joshuaeroman/plasmallmGitHub ↗★ 30QMLA Jev Decisions adapter in a KDE Plasma assistant widget for displaying structured judgments.
- blakestone-x/jev-mcpGitHub ↗★ 25PythonWraps Jev classification, scoring, yes/no judgments and candidate matching as MCP tools.
- anpicasso/hermes-jev-approvalsGitHub ↗★ 23PythonAn experimental Hermes command-approval provider for the auxiliary.approval task only.
- valentynkit/jev-commitGitHub ↗★ 17Pythonpre-commit hook: one Jev call judges whether your commit message matches the diff, plus debug leftovers, scope creep, and a secret belt
- kylemclaren/jevqlGitHub ↗★ 14GoAdds Jev semantic filtering, grouping, and ranking around ordinary PostgreSQL without installing a database extension.
- Nyarlathoteppppp/pi-heedGitHub ↗★ 14TypeScriptRuntime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.
- WiktorB2004/llama-index-jevGitHub ↗★ 8PythonProvides Jev rerankers and routers for LlamaIndex to score retrieved passages or select query tools.
- CodeAlive-AI/mastra-jev-moderationGitHub ↗★ 7TypeScriptInput moderation for Mastra agents on TypeSafe Jev — one file
- HyunjunJeon/jev-judgmentGitHub ↗★ 6PythonAdds judgment checks for authorization, operation risk, and failure causes to coding Agents.
- Stumble/jev-goGitHub ↗★ 6GoCommunity Go SDK for TypeSafe AI Jev / System One
- Kelbie/hunchGitHub ↗★ 6TypeScriptSemantic code review with Jev, plain-English rules and Agent Skills.
- alterhq/typesafe-sdk-swiftGitHub ↗★ 5SwiftUnofficial Swift library for the TypeSafe API
- andrelandgraf/safer-with-jevGitHub ↗★ 5TypeScriptAn HTTP inspection gateway that checks request content with Jev before optionally forwarding it to an HTTPS destination.
- AkashPriyadarshii/jev-scoutGitHub ↗★ 5RustA repository and Rust crate search tool that asks Jev to score and select retrieved candidates for a request.
- ariel-frischer/jevkitGitHub ↗★ 5RustFast Rust CLI for TypeSafe Jev: typed decisions, offline linting before you pay
- AkashPriyadarshii/jev-gitGitHub ↗★ 4RustSub-second Git pre-commit & pre-push semantic reflex gate powered by TypeSafe AI Jev
- mgaitan/sqlite-jevGitHub ↗★ 4CBatched natural-language judgments for SQLite, powered by TypeSafe Jev
- bitnovus/jev-spam-evalGitHub ↗★ 3Jupyter NotebookZero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines
- edgardcham/hunchoGitHub ↗★ 2TypeScriptDecisions as code on System One models: typed questions, thresholds with hysteresis, nested decisions, journal, calibration
- rajivkuriakose/typesafe-jev-examplesGitHub ↗★ 1PythonWorked examples for TypeSafe's Jev System One decision model, runnable today through OpenRouter
- djev.devGitHub ↗★ 0—A judgment service for text and images with a playground and API — one of the direct Jev alternatives.
- dakdevs/decide-mcpGitHub ↗★ 0TypeScriptConfigurable decision MCP server with AI SDK, Jev, percentage scores, and bias profile routing
Indexed in the Jev community ecosystem directory, data snapshot 2026-11-02.
Frequently asked questions
What is Integrations & bridges?
"Integrations & bridges" is a project category in the Jev ecosystem with 52 projects listed. Wiring Jev into existing data sources and protocol stacks such as Postgres and ACP/MCP.
Which projects in "Integrations & bridges" should I look at first?
Sorted by stars, start with: agentgateway/agentgateway, typesafe-ai/skills, vellum-ai/vellum-assistant, realZachi/pg-jev, kentcdodds/kody. Each has its own page covering positioning, language, license and alternatives in the same category.
Other categories
Keep going on this site
Try, docs, cases, and pricing link to each other. The next page is on this site.
- Site directoryThe full list of the pages above.
- EcosystemCommunity projects by category.
- Jev coverageEach entry names the decision and its evidence.
- Daily casesThe next batch of coverage cases, each day.
- CommunityPublic posts, each with its source.
- BuildsNotes on model and site updates.
- PrimitivesChoice, Noul, and Score together.
- PatternsRouting, fan-out, and composite scoring.
- SDKsHTTP, Python, and JavaScript.
Use clavue-jev
- Try a judgmentSend a state and read the answer.
- Live scenesTetris, six rapid judgments, and a sort. Copy the call and run it again.
- Judgment LabSupport triage, release review, compliance routing — edit and run on the spot.
- Compareclavue-jev and jev-1.13.0 answer the same question.
- DemosJudgment examples you can edit.
- PricingInput is $0.042 per million tokens. Output is free.
- APICall POST /v1/judge with a key.
Docs
- IntroductionWhat this model is for.
- Quick startThe smallest call that runs.
- System OneWritten here: a state plus one typed question. The model is clavue-jev.
- StateThe text you send in.
- ConfidenceHow sure the answer is, and when to act on it.
- ChoicePick one mutually exclusive option.
- NoulA yes/no question, returned as the probability of yes.
- ScoreRate along a scale.
- Intent routingOne Choice call dispatches the request.
- Confidence routingAct when confidence is high. Hand off when it is low.
- Fan-outAsk several questions of one state.
- Composite scoringFold several scores into one ranking.
- HTTP APIThe request shape without an SDK.
- Python SDKCall a judgment from Python.
- JavaScript SDKCall a judgment from JavaScript.
Cases
- Use-case mapWhich primitive people use for which job.
- GuardrailsA yes/no check before an action runs.
- Function callingPick which function to call.
- Classify with confidenceDo not act when the class is unsure.
- Semantic findFind the passages that match.
- Parallel questionsAsk the whole set in one call.
- Hierarchical classificationCoarse class first, then the fine one.
- Citation checkWhether a sentence is supported by the source.
- Entity alignmentWhether two names are the same thing.
- Skill suggestionChoose which skill fits the moment.