JevCode / Ecosystem

Ecosystem

Public projects built around Jev and the TypeSafe System One model. Filter by category and language.

• yibie/awesome-jevCurated listsGitHub ↗★ 2.5kPythonA curated list of public projects, integrations, and discussions built on Jev.
• v-modal/awesome-jev-toolsCurated listsGitHub ↗★ 754—A category-paged list of Jev projects and practices, with stated inclusion criteria and per-entry evidence checks (real API calls, runnable checks, sourced numbers).What Jev does here Does not judge decision points itself; it requires every entry to name the step where Jev makes a typed judgment and to show checkable call evidence.
• AbdelStark/awesome-typesafeCurated listsGitHub ↗★ 613CSSCurated list of official resources and community projects for TypeSafe, System One models, and Jev.
• Anil-matcha/awesome-jev-by-typesafeCurated listsGitHub ↗★ 2PythonEvidence-backed use cases, patterns, prompts, and starter code — the broadest Jev resource collection.
• virattt/ai-hedge-fundAgents & workflowsGitHub ↗★ 64.4kPythonAn educational AI hedge-fund prototype with an optional Jev adapter for structured judgments in fund decision workflows.What Jev does here Converts strategy questions to System One requests and normalizes native answers to the project’s result format.
• trycua/cuaAgents & workflowsGitHub ↗★ 31.5kRustCua’s preview jev-use example pairs Driver observation and execution with bounded Jev browser-action choices.What Jev does here Reads DOM or supported visual-region descriptions and returns a supplied candidate action ID.
• browser-use/jev-ultrafastAgents & workflowsGitHub ↗★ 24.0kPythonA browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.What Jev does here Chooses an action and its matching DOM element in one request; a text model generates input text.
• vercel-labs/json-renderAgents & workflowsGitHub ↗★ 18.9kTypeScriptA Jev UI-composition experiment inside the json-render website that selects from predefined component and property options.What Jev does here Evaluates component configurations through Vercel AI Gateway, then composeSpec assembles the UI specification.
• jaredpalmer/kevAgents & workflowsGitHub ↗★ 9.8kPythonTiny Jev-like decision head built atop Qwen2.5-0.5B that can be trained and run locally on Apple Silicon MacBooks.What Jev does here Attaches a parallel decision head to an open 0.5B model to answer discrete questions directly from token activations.
• lahfir/agent-desktopAgents & workflowsGitHub ↗★ 6.9kRustAn optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data.What Jev does here Jev selects a target and action and estimates presence and risk; local policy decides whether to execute.
• jarrodwatts/jev-traderAgents & workflowsGitHub ↗★ 3.1kTypeScriptA market-making experiment on Kuru’s MON-USDC book on Monad, with optional per-block Jev buy/sell decisions.What Jev does here In Jev mode, order-book judgments feed code that simulates fills or submits configured post-only limit orders.
• TianyuCodings/NanoJevAgents & workflowsGitHub ↗★ 2.6kPythonNano replica of Jev featuring parallel decisions, dynamic candidate sets, and an end-to-end training and evaluation pipeline.What Jev does here Evaluates multiple questions and dynamic candidate spaces concurrently in a single forward pass, logging navigation choices.
• awlevin/typesafe-computer-useAgents & workflowsGitHub ↗★ 1.3kPythonBuilds candidate actions from OCR and UI state for Jev to control macOS, calling a text model only when writing is needed.What Jev does here Selects the next step from deterministically extracted controls and actions before desktop execution.
• wy-coliney/jev-browser-useAgents & workflowsGitHub ↗★ 1.2kJavaScriptA Skill for Codex browser workflows: Jev chooses navigation, clicks, and scrolling while Codex handles text input and final checks.What Jev does here Sends page state and permitted candidates to Jev; the existing browser connection executes the actions.
• CelestoAI/celestoAgents & workflowsGitHub ↗★ 1.1k—A Celesto PR-review example prepares sandbox checks and compares a general model with Jev on candidate findings.What Jev does here Judges whether a finding was introduced by the change, is supported and merits a fix.
• thruwire/foremanAgents & workflowsGitHub ↗★ 803PythonSoftware Factory Foreman based on the TypeSafe Jev model.What Jev does here AsyncTypeSafeClient.system_one with default jev-latest sends Noul questions for supervision.
• uezo/aiavatarkitAgents & workflowsGitHub ↗★ 703—An optional AIAvatarKit component uses Jev to judge turn endings from speech transcripts.What Jev does here Assesses utterance completeness and whether the user is likely to continue speaking.
• devagrawal09/jev-reviewAgents & workflowsGitHub ↗★ 695TypeScriptA staged code-review workflow and local dashboard built with TypeSafe Jev.What Jev does here Judges risk, files, evidence regions, mechanisms and severity before rule-based reviewer routing.
• Sac-Y/Jev-cuAgents & workflowsGitHub ↗★ 631JavaScriptA Codex Computer Use loop sending text candidates to Jev while desktop tools observe and act.What Jev does here Chooses targets and actions and assesses completion and risk; local policy controls execution or confirmation.
• BennyKok/omg.devAgents & workflowsGitHub ↗★ 553TypeScriptAn omg.dev mobile testing script can use Jev to read the accessibility tree and choose the next interaction.What Jev does here Chooses controls and checks completion or blockage before the test runner operates the UI.
• kyotofin/tax-doc-classifierAgents & workflowsGitHub ↗★ 515TypeScriptA tax-document page classifier that uses Jev to choose from predefined IRS form and page categories.What Jev does here Extracts PDF page text and sends it to Jev for form type, page type, and confidence.
• droidrun/mobile-jevAgents & workflowsGitHub ↗★ 459—Controls an Android phone through Mobilerun, with a web studio and CLI showing Jev decisions.What Jev does here Chooses apps, controls and next actions from phone state; Mobilerun executes them.
• fhshaik/typesafe-marioAgents & workflowsGitHub ↗★ 457PythonA TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.What Jev does here Reads motion, enemies, terrain and recent controls, then selects a predefined legal action.
• moritzkremb/jev-voice-browserAgents & workflowsGitHub ↗★ 422—Controls a Playwright browser by sending incremental speech transcripts to Jev.What Jev does here Chooses intent, elements, URLs or verbatim spans and judges command completeness and sensitive actions.
• jkudish/jev-browserAgents & workflowsGitHub ↗★ 366—Drives a browser from a task and URL, returning the final page, screenshot and action trace.What Jev does here Chooses DOM actions and judges goal completion or stalled progress; a separate model can supply typed text.
• RomanSlack/jev-droneAgents & workflowsGitHub ↗★ 297PythonA MuJoCo drone experiment deriving scene features from camera buffers for Jev tactical advice.What Jev does here Uses range sectors, obstacle heights and target state to choose maneuvers and assess risk or target loss.
• Knuckles92/OpenWhisperAgents & workflowsGitHub ↗★ 234PythonA dictation and meeting-notes app with optional Jev checks for topic changes, note-taker instructions and sensitive text.What Jev does here Makes bounded transcript judgments for checkpoints, note-taking actions or screening before remote text cleanup.
• standardagents/jevpilotAgents & workflowsGitHub ↗★ 230JavaScriptA browser driving simulator where Jev chooses among locally generated paths and speeds.What Jev does here Jev reads road and traffic state and selects motion; geometry, collision prediction and braking remain local.
• aowang-ai/jev-tradeAgents & workflowsGitHub ↗★ 225TypeScriptAn experimental Hyperliquid trading bot using Jev to choose long or short and whether to open, close, or hold.What Jev does here Each asset account sends market state to Jev; execution code places or cancels orders based on the decisions.
• socai-io/jev-socialAgents & workflowsGitHub ↗★ 194JavaScriptJev-powered Instagram, TikTok, and LinkedIn research: typed routing, real browser evidence, streamed post cards, video capture, and cited socai reports.What Jev does here Jev returns a structured decision for the local program; consult the source for the exact decision policy.
• jexp/neo4jevAgents & workflowsGitHub ↗★ 181Jupyter NotebookNavigates a Neo4j graph one hop at a time, asking Jev which relationship to follow next.What Jev does here Choice scores neighboring relationships and Noul checks goal completion; local beam search retains candidate paths.
• agent-labs-dev/fastbrowseAgents & workflowsGitHub ↗★ 173PythonA fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.
• irfndi/prism-liquidity-agentAgents & workflowsGitHub ↗★ 131TypeScriptA Solana liquidity Agent with Jev shadow judgments compared against rule-based decisions.What Jev does here Evaluates entry distribution, toxic flow, holding and stress signals for calibration logs.
• Ying-Kai-Liao/jev-browserAgents & workflowsGitHub ↗★ 128JavaScriptA browser library, CLI and MCP server where the caller supplies goals and text while Jev selects actions.What Jev does here Chooses elements, actions and values, and assesses completion, errors and irreversible steps.
• trungdq88/youtube-sponsor-detectionAgents & workflowsGitHub ↗★ 116JavaScriptYouTube extension detecting sponsored segments from live audio and transcripts using Jev, skipping promotional blocks automatically.What Jev does here Inspects transcript segments with Jev to identify sponsor reads while browser code handles playback timeline skipping.
• ChetasLua/jevmeterAgents & workflowsGitHub ↗★ 110PythonCreates edited videos with score meters by asking Jev to rate transcript sentences against selected rubrics.What Jev does here Scores transcript sentences with preset questions and scales for meters placed on the video timeline.
• vinilana/jev-eval-agentAgents & workflowsGitHub ↗★ 109HTMLAgent tool evaluation harness comparing standard LLM tool selection against Jev routing across 100 mocked tools.What Jev does here Employs Jev for two-stage discrete pruning over tool catalogs, narrowing extensive tool lists down to relevant candidates in milliseconds.
• ellipsis-dev/blinkAgents & workflowsGitHub ↗★ 101TypeScriptFinds files from a natural-language query using multiple walkers through the directory tree.What Jev does here Jev scores file and directory names; code distributes walkers using those probabilities.
• AkashPriyadarshii/jev-seoAgents & workflowsGitHub ↗★ 97RustAn experimental Rust SEO/GEO CLI and MCP tool combining page checks, DuckDuckGo queries and optional Jev scoring.What Jev does here Classifies search intent, direct answers and content gaps, with a custom citation-likelihood rubric.
• realZachi/typesafe-adblockAgents & workflowsGitHub ↗★ 94JavaScriptAn experimental Chrome extension that asks Jev whether candidate DOM elements are ads, then highlights or removes them.What Jev does here Batches element text, labels, and link information into Noul questions and applies a threshold.
• AboveColin/HA-JevAgents & workflowsGitHub ↗★ 82PythonTurns Jev judgments into Home Assistant sensors, such as checking whether finished laundry has been left unattended.What Jev does here Reads selected entity states and returns probabilities, choices, or scores that configured thresholds can use in automations.
• yikangy873-gif/jev-desktopAgents & workflowsGitHub ↗★ 79JavaScriptTypeSafe Jev action selection inside Codex Computer Use
• OmniJev/PlayJevAgents & workflowsGitHub ↗★ 63JavaScript🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.
• zadescoxp/Jev-TradesAgents & workflowsGitHub ↗★ 57PythonA dashboard combining live crypto market data with Jev-guided paper trading; no broker or live-order API is connected.What Jev does here Jev reviews completed minute candles and indicators; Python applies confidence and position limits to a simulated portfolio.
• RafalWilinski/vibecheckAgents & workflowsGitHub ↗★ 50JavaScriptShows a Jev scorecard before posting on X, assessing draft clarity, tone, and possible offensiveness.What Jev does here Sends the draft and reply or quote context to Jev for multiple scores and a posting suggestion.
• unicodeveloper/jevocksAgents & workflowsGitHub ↗★ 48TypeScriptEveryday Stocks Status with Jev
• chy4pro/jev-for-chromeAgents & workflowsGitHub ↗★ 46TypeScriptJev for Chrome: drives the tab you are looking at with TypeSafe Jev, a sub-second decision model. Community port of browser-use/jev-ultrafast, not affiliated with TypeSafe.
• valentynkit/jev-belayAgents & workflowsGitHub ↗★ 44JavaScriptClaude Code Stop hook that blocks an unverified done: reads the transcript for evidence, asks Jev once, fails open on everything elseWhat Jev does here Four questions: whether the closing message claims done, claims checks passed, whether verification applies, and a complete / partial / blocked / other choice.
• AkashPriyadarshii/jev-superpowersAgents & workflowsGitHub ↗★ 39JavaScriptSystematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisionsWhat Jev does here Invokes Jev at workflow checkpoints to evaluate change validity, test sufficiency, and package safety before advancing agent state.
• devanshbatham/commit-minerAgents & workflowsGitHub ↗★ 38RustClassifies Git commit messages and diffs with Jev for bug fixes, security fixes, CWEs, and change types.What Jev does here Asks fixed-category questions about commits and saves results for filtering and HTML/CSV reports.
• hqman/JevScoutAgents & workflowsGitHub ↗★ 38PythonA demo job-search Skill for coding Agents that browses company careers pages in Chrome, uses Jev to screen AI and software-engineering roles, and saves the results.What Jev does here Jev uses Choice to classify pages and Noul to assess careers links, role relevance, filter controls and candidate fit; local thresholds select navigation, job details and saved results.
• AlbionaHoti/refgardenAgents & workflowsGitHub ↗★ 37TypeScriptA visual-reference gallery drawing from The Met, NASA and Cosmos, with Jev in local Explore mode.What Jev does here Jev selects search phrases and highlights references using titles and descriptions, not image pixels.
• DanRWilloughby/snifftestAgents & workflowsGitHub ↗★ 36TypeScriptA Markdown and plain-text prose linter using local rules and optional Jev judgments.What Jev does here Assesses paragraphs against style rules such as redundant closings, clichés and excessive hedging.
• compozy/yoshiAgents & workflowsGitHub ↗★ 31TypeScriptContext-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozyWhat Jev does here Intercepts request payloads and uses Jev to score historical messages, discarding outdated tool noise before forwarding to upstream LLMs.
• phyous/tsai-scAgents & workflowsGitHub ↗★ 28PythonA Jev harness for StarCraft shareware’s Strongarm mission, pausing the game during state reads and inference.What Jev does here Selects commands from structured game state and executes them with mouse and keyboard input.
• sorrycc/typesafe-snakeAgents & workflowsGitHub ↗★ 24TypeScriptSnake autoplayer driven by TypeSafe Jev, executing one discrete System One decision per tick with code-enforced legal moves.What Jev does here Supplies board state, fruit location, and legal direction choices to Jev, selecting the optimal move direction each tick.
• gaborishka/jev-canvasAgents & workflowsGitHub ↗★ 22JavaScriptDraw on a tldraw canvas with your voice and a pointing finger. Jev (TypeSafe System One) decides action, target and place in ~350 ms per spoken word.
• sosopop/jev_stockAgents & workflowsGitHub ↗★ 16PythonAn experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.
• forvela/jev-agent-browserAgents & workflowsGitHub ↗★ 15JavaScriptFast, bounded browser agents powered by Jev and agent-browser — typed actions, research, classification, and safe orchestration.
• 24601/AugustusAgents & workflowsGitHub ↗★ 13PythonAgent skill: design judgment-assisted systems with TypeSafe Jev (System One). Maps Choice/Score/Noul onto decision theory, reranking, and routing. Composition algebra, question design, validation gates. MIT.
• HyunjunJeon/pi-quiet-askAgents & workflowsGitHub ↗★ 12TypeScriptTypeSafe Jev as the pi coding agent's quiet decision layer
• joelhooks/pi-fast-jev-compactionAgents & workflowsGitHub ↗★ 12TypeScriptPi extension: verbatim context compaction with TypeSafe Jev decisionsWhat Jev does here Judges whether calls and outputs should survive in the context sent to the model.
• leonaaardob/fast-dev-compactionAgents & workflowsGitHub ↗★ 12TypeScriptCodex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.What Jev does here Assesses past conversation turns with Jev when context limits approach, selecting critical tool outputs and user requirements for retention.
• valentynkit/jev-plays-pokemon-redAgents & workflowsGitHub ↗★ 9PythonPokemon Red on PyBoy: code owns the route and the arithmetic, Jev picks at branches in about 100 ms, calibration measured instead of assumedWhat Jev does here A Choice over legal actions at each branch; battle turns also ask Noul faints_this_turn and should_flee; failures take the code default.
• noplan-inc/limpetAgents & workflowsGitHub ↗★ 7PythonA Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev.
• milanboers/jev-plays-pokemonAgents & workflowsGitHub ↗★ 6PythonPlaying Pokemon Red using TypeSafe Jev
• shitianfang/wakegateAgents & workflowsGitHub ↗★ 6TypeScriptAsk Jev whether a sleeping agent's wakeup is worth a full LLM turn before you resume it. A fail-open wake gate for long-running agents on Workers, Durable Objects and Node.
• legacybridge-tech/pi-typesafe-jevAgents & workflowsGitHub ↗★ 3TypeScriptA pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions.
• kxzk/typesafe-jev-drone-demoAgents & workflowsGitHub ↗★ 1PythonThree.js drone simulator with a Python backend and live TypeSafe Jev navigation
• agentgateway/agentgatewayIntegrations & bridgesGitHub ↗★ 5.9kRustA Jev guardrail example in Agentgateway using a webhook to inspect model requests and responses.What Jev does here Jev scores jailbreaks, harmful content and secret disclosure; thresholds or evaluation errors reject requests.
• typesafe-ai/skillsIntegrations & bridgesGitHub ↗★ 2.9k—Agent skills for building with TypeSafe's System One API
• vellum-ai/vellum-assistantIntegrations & bridgesGitHub ↗★ 1.5kTypeScriptAn optional Jev provider in Vellum Assistant sends conversation state and explicit questions to TypeSafe.What Jev does here Submits state and question bundles to System One and returns structured answers to the Assistant.
• realZachi/pg-jevIntegrations & bridgesGitHub ↗★ 1.2kPythonAsk your Postgres tables questions in plain language — a PostgreSQL extension powered by Jev.What Jev does here Sends row content to Jev for a match decision, category, or score used by SQL conditions and ordering.
• kentcdodds/kodyIntegrations & bridgesGitHub ↗★ 887TypeScriptOptional second-stage search: widen the hybrid pool, then Score-rerank candidates with Workers AI typesafe/jev.What Jev does here Sends a Score question per candidate, reorders and drops low scores; the model id is typesafe/jev.
• AgentiLoop/AgentIntegrations & bridgesGitHub ↗★ 652SwiftAn optional Jev command-risk advisor inside a native macOS Agent, with a TypeSafeKit client.What Jev does here Adds a destructive-risk judgment after local shell checks and refuses commands above the configured threshold.
• jkudish/jev-mcpIntegrations & bridgesGitHub ↗★ 562TypeScriptEight MCP tools for evidence checks, content screening, search, reranking, classification, comparison and extraction.What Jev does here Uses typed questions to assess evidence support, content risk and candidate relevance.
• superagents-lab/jev-searchIntegrations & bridgesGitHub ↗★ 550—Searches the web with Jev choosing sources and time ranges, then ranking returned links.What Jev does here Judges search intent, source and time settings, and relevance of individual results.
• dabit3/jev-experimentsIntegrations & bridgesGitHub ↗★ 412TypeScriptA collection of Jev developer-tool experiments, including Commit Sentry for semantic checks on staged diff hunks.What Jev does here Judges risks such as exposed credentials or destructive changes; local rules warn or block a commit.
• kitze/unclutterIntegrations & bridgesGitHub ↗★ 387TypeScriptA browser extension using Jev to identify ads, promotions, and subscription popups and save reusable hiding rules.What Jev does here Evaluates candidate page elements before the extension applies local hiding rules.
• itsmostafa/typesafe-mcpIntegrations & bridgesGitHub ↗★ 357GoAn MCP server that lets Claude Code, Claude Desktop, Codex and Pi ask Jev typed questions.What Jev does here Submits state and Choice, Score or Noul questions and returns structured answers with probabilities.
• QuentinCody/interlinked-cliIntegrations & bridgesGitHub ↗★ 182—Interlinked adds optional Jev judgments and evidence checks to local coding-agent checks.What Jev does here Assesses inputs such as test names, documentation claims and supporting evidence.
• DevMortimer/pi-wardenIntegrations & bridgesGitHub ↗★ 177TypeScriptAdds checks for project rules, out-of-scope actions, repeated failures, and completion claims to Pi Agents.What Jev does here Uses Jev to judge rule violations, irreversible actions, and task drift, feeding results back to the Agent.
• y0usaf/pi-jevIntegrations & bridgesGitHub ↗★ 165TypeScriptA Pi extension that flags tool risks before execution and checks output for secrets and failure types.What Jev does here Jev scores destructive actions, scope and output risks; configuration chooses warnings or confirmation.
• uehaj/jev-semgrepIntegrations & bridgesGitHub ↗★ 150JavaScriptA semantic grep that scores each line with Jev against a meaning, including AND/OR/NOT and cross-language queries.What Jev does here Batches about thirty lines and asks jev-latest a Score or Noul per line for the stated meaning.
• leepokai/jev-guardIntegrations & bridgesGitHub ↗★ 144JavaScriptTool-call checks for coding Agents that assess operation risk, user intent and prompt-injection signals.What Jev does here Jev evaluates tool inputs or outputs in session context; local rules allow, warn or block.
• devagrawal09/stanley-codeIntegrations & bridgesGitHub ↗★ 119TypeScriptBounded TypeSafe Jev workflows for coding agents.
• AkashPriyadarshii/jev-curateIntegrations & bridgesGitHub ↗★ 107RustA Rust dataset-filtering experiment using Jev scores to keep or reject text records.What Jev does here Runs local prefilters, calls TypeSafe and applies probability and score thresholds to each record.
• pithings/advocaatIntegrations & bridgesGitHub ↗★ 101TypeScriptA small, type-safe client for asking AI questions about your data.What Jev does here Combines yes/no, Choice and Score questions and maps responses to typed values.
• giuliosmall/pg_typesafeIntegrations & bridgesGitHub ↗★ 84CA pre-alpha PostgreSQL C extension for calling Jev from SQL for classification, yes/no judgments, and scoring.What Jev does here Converts SQL input into System One requests and returns answers through database functions.
• CaptainCore/captaincoreIntegrations & bridgesGitHub ↗★ 76GoJev commands in the WordPress toolkit CaptainCore answer structured questions and prioritize malware scanner findings for review.What Jev does here Sends scan rules, matched snippets, and file context to Jev to assess likely true positives and suggested handling.
• TheoOliveira/pi-jevIntegrations & bridgesGitHub ↗★ 72TypeScriptHelps Pi Agents find tools and skills for a task, with structured evaluation and optional history filtering.What Jev does here Judges how candidate tools, skills, and history relate to the task so local rules can load or retain them.
• shitianfang/jev-useIntegrations & bridgesGitHub ↗★ 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 LLMWhat Jev does here Jev returns a structured decision for the local program; consult the source for the exact decision policy.
• getsynkora/synkora-aiIntegrations & bridgesGitHub ↗★ 55—Synkora includes optional TypeSafe client tools for classification, scoring and yes/no judgments.What Jev does here Sends workflow state and named questions to Jev and returns structured answers to agents.
• brainstormity/Jev-Moderation-BotIntegrations & bridgesGitHub ↗★ 50PythonA Discord moderation bot using Jev to check spam and scam links, with local warning and timeout rules.What Jev does here Assesses messages or recent member history; the bot applies deletion, warnings or timeouts.
• DevMortimer/pi-typesafeIntegrations & bridgesGitHub ↗★ 48TypeScriptA Pi Jev extension providing a decision tool, terminal playground commands and an API for other extensions.What Jev does here A shared client batches typed questions, validates responses and records usage and availability.
• gamesonrblx/JevbridgeIntegrations & bridgesGitHub ↗★ 47TypeScriptACP and MCP adapter bridging Jev with any LLM — typed decisions alongside Codex, Claude, Grok, and OpenCode.What Jev does here Sends state and bounded questions to the chosen backend, with an offline rule backend also available.
• tacticocc/JevbridgeIntegrations & bridgesGitHub ↗★ 47TypeScriptACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
• dannote/jevIntegrations & bridgesGitHub ↗★ 37ElixirTypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answerWhat Jev does here Sends state and typed questions to TypeSafe, then delivers answers as messages.
• jomatsu/pi-jev-auto-modeIntegrations & bridgesGitHub ↗★ 33TypeScriptAdds rule checks to Pi commands and file operations, then uses Jev to assess cases that need further judgment.What Jev does here Local rules handle explicit denies and allows before Jev assesses authorization and risk for bash, write, and edit.
• joshuaeroman/plasmallmIntegrations & bridgesGitHub ↗★ 30QMLA Jev Decisions adapter in a KDE Plasma assistant widget for displaying structured judgments.What Jev does here Converts the current message into decision questions and receives answers from TypeSafe or a compatible Decisions endpoint.
• blakestone-x/jev-mcpIntegrations & bridgesGitHub ↗★ 25PythonWraps Jev classification, scoring, yes/no judgments and candidate matching as MCP tools.What Jev does here The MCP server calls the TypeSafe SDK and returns choices, probabilities and scores.
• anpicasso/hermes-jev-approvalsIntegrations & bridgesGitHub ↗★ 23PythonAn experimental Hermes command-approval provider for the auxiliary.approval task only.What Jev does here Jev returns APPROVE, DENY or ESCALATE, with local thresholds and policy determining handling.
• valentynkit/jev-commitIntegrations & bridgesGitHub ↗★ 17Pythonpre-commit hook: one Jev call judges whether your commit message matches the diff, plus debug leftovers, scope creep, and a secret beltWhat Jev does here Five Noul questions in one request: checkable message, hunk match, debug leftovers, unmentioned work, and credential-shaped added lines. Default blocking is the regex belt; secret_shaped participates only under --strict.
• kylemclaren/jevqlIntegrations & bridgesGitHub ↗★ 14GoAdds Jev semantic filtering, grouping, and ranking around ordinary PostgreSQL without installing a database extension.What Jev does here The CLI or service layer evaluates jev_* calls over row text before completing the query.
• Nyarlathoteppppp/pi-heedIntegrations & bridgesGitHub ↗★ 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-jevIntegrations & bridgesGitHub ↗★ 8PythonProvides Jev rerankers and routers for LlamaIndex to score retrieved passages or select query tools.What Jev does here Uses Score for passage relevance and Choice for selecting query engines or tools.
• CodeAlive-AI/mastra-jev-moderationIntegrations & bridgesGitHub ↗★ 7TypeScriptInput moderation for Mastra agents on TypeSafe Jev — one file
• HyunjunJeon/jev-judgmentIntegrations & bridgesGitHub ↗★ 6PythonAdds judgment checks for authorization, operation risk, and failure causes to coding Agents.What Jev does here Uses conversation and command results to assess whether to ask the user, whether an action exceeds scope, and whether to retry.
• Stumble/jev-goIntegrations & bridgesGitHub ↗★ 6GoCommunity Go SDK for TypeSafe AI Jev / System OneWhat Jev does here Sends application state and questions to Jev and parses Choice, Score or Noul answers.
• Kelbie/hunchIntegrations & bridgesGitHub ↗★ 6TypeScriptSemantic code review with Jev, plain-English rules and Agent Skills.
• alterhq/typesafe-sdk-swiftIntegrations & bridgesGitHub ↗★ 5SwiftUnofficial Swift library for the TypeSafe API
• andrelandgraf/safer-with-jevIntegrations & bridgesGitHub ↗★ 5TypeScriptAn HTTP inspection gateway that checks request content with Jev before optionally forwarding it to an HTTPS destination.What Jev does here Jev judges prompt injection or unsafe content; local rules forward, flag or block the request.
• AkashPriyadarshii/jev-scoutIntegrations & bridgesGitHub ↗★ 5RustA repository and Rust crate search tool that asks Jev to score and select retrieved candidates for a request.What Jev does here Compares candidate information with the request, scores fit and maintenance signals, and chooses a candidate.
• ariel-frischer/jevkitIntegrations & bridgesGitHub ↗★ 5RustFast Rust CLI for TypeSafe Jev: typed decisions, offline linting before you pay
• AkashPriyadarshii/jev-gitIntegrations & bridgesGitHub ↗★ 4RustSub-second Git pre-commit & pre-push semantic reflex gate powered by TypeSafe AI Jev
• mgaitan/sqlite-jevIntegrations & bridgesGitHub ↗★ 4CBatched natural-language judgments for SQLite, powered by TypeSafe Jev
• bitnovus/jev-spam-evalIntegrations & bridgesGitHub ↗★ 3Jupyter NotebookZero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines
• edgardcham/hunchoIntegrations & bridgesGitHub ↗★ 2TypeScriptDecisions as code on System One models: typed questions, thresholds with hysteresis, nested decisions, journal, calibration
• rajivkuriakose/typesafe-jev-examplesIntegrations & bridgesGitHub ↗★ 1PythonWorked examples for TypeSafe's Jev System One decision model, runnable today through OpenRouter
• djev.devIntegrations & bridgesGitHub ↗★ 0—A judgment service for text and images with a playground and API — one of the direct Jev alternatives.What Jev does here Sends text or image state plus typed questions to a judgment endpoint and returns typed answers with probabilities.
• dakdevs/decide-mcpIntegrations & bridgesGitHub ↗★ 0TypeScriptConfigurable decision MCP server with AI SDK, Jev, percentage scores, and bias profile routing
• Mapika/deciderResearch & reimplementationGitHub ↗★ 1.2kPythonA family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.
• wfzyx/vonResearch & reimplementationGitHub ↗★ 923PythonThe open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.
• YannQi/R-4BResearch & reimplementationGitHub ↗★ 186—A 4B open decision model (Reflex-4b): benchmarked at 2-3x faster than Jev with roughly 5% lower accuracy, Apache 2.0.What Jev does here Loads 4B weights locally, takes state plus typed questions, and returns calibrated probabilities in one forward pass.
• kshetrajna12/reflexResearch & reimplementationGitHub ↗★ 174PythonA small open decision model: state + typed questions → calibrated probabilities, re-created on Qwen3.5.
• ikermoel/open-alternative-jevResearch & reimplementationGitHub ↗★ 74PythonOpen-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks
• Mapika/decider-2bResearch & reimplementationGitHub ↗★ 60—A 2B open decision model (Decider-2b): benchmarked at ~10x faster than Jev, fully local, roughly 5% lower accuracy.What Jev does here Runs 2B weights locally: state plus typed questions to calibrated probabilities, suited to fully offline judging.
• r-ms/mini-jevResearch & reimplementationGitHub ↗★ 60Pythonmini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.
• zhengxuyu/litjevResearch & reimplementationGitHub ↗★ 47PythonTurn any off-the-shelf LLM into a Jev -like decision layerWhat Jev does here Implements the /v1/systemone endpoint (Choice, Score, Noul) by calculating candidate token log-probabilities without text generation.
• zhihz/openjevResearch & reimplementationGitHub ↗★ 37PythonLocal bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.
• GiesN/typesafe-jev-workflowResearch & reimplementationGitHub ↗★ 11PythonAn async LangGraph example that classifies mocked emails as invoice-related or general.What Jev does here Jev returns invoice or general; graph nodes choose the corresponding demo handler.
• us/jev-localResearch & reimplementationGitHub ↗★ 9PythonLocal Jev-compatible evaluation server: POST /v1/systemone with typed noul/choice/score, open weights, no waitlist
• scienthoon/jev-ood-calibrationResearch & reimplementationGitHub ↗★ 6PythonIndependent calibration test of TypeSafe's Jev on a task it cannot have seen: 900 rule-generated support tickets (choice / score / boolean) plus 3 public benchmarks via Vercel AI Gateway. Raw responses, ECE with noise floor, temperature refit, per-type sign of miscalibration. Reproducible for ~$0.06.
• jgridifier/jev-research-evalResearch & reimplementationGitHub ↗★ 3HTMLReproducible Jev Ultrafast research-browser eval harness + field note (QC’d cases, suite runner, report generator). Not investment advice.
• ably-labs/jev-pongResearch & reimplementationGitHub ↗★ 1TypeScriptPong where the ball moves one step per model decision. Jev vs LLMs via Vercel AI Gateway, every player and agent on an Ably channel.
• miounet11/openjevResearch & reimplementationGitHub ↗★ 0—Can we run something like Jev on a 3090 at home?
• yodablocks/jev-orderby-benchResearch & reimplementationGitHub ↗★ 0PythonDoes ORDER BY over a Jev probability put rows in a defensible order? Independent ranking, calibration and invariant measurements of TypeSafe AI's Jev: passes six pre-registered gates on 360 labeled rows, fails four of six on graded product relevance.
• langchain-ai/langchainToolingGitHub ↗★ 148.8kPythonAn optional Jev classifier integration for Python LangChain workflows.What Jev does here Submits binary, categorical and ordered-score questions and returns typed answers with probabilities.
• BerriAI/litellmToolingGitHub ↗★ 62.5k—LiteLLM can use Jev to classify requests for its complexity-based model router.What Jev does here Maps requests to configured complexity classes that drive backend routing.
• can1357/oh-my-piToolingGitHub ↗★ 37.4k—Oh My Pi includes an optional TypeSafe judgment provider for bounded decisions in coding-agent workflows.What Jev does here Sends agent state and typed questions to Jev and parses structured answers.
• davila7/claude-code-templatesToolingGitHub ↗★ 33.0kPythonA community Claude Code Templates mod that uses Jev to suggest subagent models and reasoning levels.What Jev does here Evaluates task tier, reasoning needs and production risk; local policy maps results to invocation settings.
• ComposioHQ/composioToolingGitHub ↗★ 30.9kTypeScriptAn optional TypeSafe provider for Composio that uses Jev to choose among tools and bounded argument options.What Jev does here Turns tool or action conditions into structured questions and passes Jev answers to local invocation logic.
• vercel/aiToolingGitHub ↗★ 27.7kTypeScriptThe TypeSafe provider in AI SDK lets TypeScript applications call Jev through the shared evaluate interface.What Jev does here Maps choice, score, and yes/no questions to TypeSafe System One requests and parses typed results.
• pydantic/pydantic-aiToolingGitHub ↗★ 21.0kPythonAn optional TypeSafe provider and Jev model integration for Pydantic AI.What Jev does here Converts supported structured output fields into typed Jev questions and maps answers back to the output model.
• elizaOS/elizaToolingGitHub ↗★ 19.8kTypeScriptAn optional TypeSafe HTTP adapter in Eliza’s source, not registered with the Agent runtime by default.What Jev does here Only an explicit systemOne call sends state and questions, returning validated typed answers.
• langchain-ai/langchainjsToolingGitHub ↗★ 18.3kTypeScriptAn optional LangChain.js TypeSafeClassifier integration for sending state and predefined questions to Jev.What Jev does here Uses invoke to call TypeSafe and parse choice, noul, score and probability fields.
• openchamber/openchamberToolingGitHub ↗★ 12.4kTypeScriptOpenChamber’s optional automatic model router uses Jev to classify a message before selecting a configured model and reasoning level.What Jev does here Jev selects a task category; local category mappings determine the model configuration.
• 0xPlaygrounds/rigToolingGitHub ↗★ 9.0kRustAn experimental TypeSafe crate in Rig for expressing Jev questions and answers with Rust types.What Jev does here Sends application state and questions to Jev and parses Choice, Score or Noul answers.
• kunchenguid/firstmateToolingGitHub ↗★ 8.5kShellFirstmate can optionally use Jev to match task briefs to dispatch rules before local policy chooses an Agent configuration.What Jev does here Sends the task brief and candidate rules to Jev, then resolves execution profiles with confidence and local conditions.
• tamaratran/fast-jev-compactionToolingGitHub ↗★ 7.8kTypeScriptClaude Code plugin replacing compaction summaries with Jev decisions — each tool call scored in one fast request, stale ones dropped, kept content verbatim.What Jev does here Separately judges whether a tool call and its full output are still needed; code keeps, truncates or drops them.
• latitude-dev/latitude-llmToolingGitHub ↗★ 4.7k—Latitude includes an optional Jev preclassifier for conversation checks and their selection records.What Jev does here Judges which checks apply and can add checks when thresholds and rate limits permit.
• ax-llm/axToolingGitHub ↗★ 3.0k—Ax provides a TypeSafe integration for boolean or finite-class signatures and native Jev answers.What Jev does here Maps supported signatures to Jev questions or sends native System One requests.
• bastani-inc/atomicToolingGitHub ↗★ 873TypeScriptAn optional Jev decision backend in the Atomic coding Agent for bounded structured choices such as routing.What Jev does here Sends predefined questions to Jev and decodes answers for callers; regular models still generate code.
• gargpratyush/jev-routerToolingGitHub ↗★ 649JavaScriptA Claude Code and CLI proxy that asks Jev to score task complexity and pick a model from the account’s available set.What Jev does here Scores task, reasoning, and tool complexity, then chooses among the exact models the account can run; failures keep the current model.
• featherless-ai/simple-jevToolingGitHub ↗★ 636PythonAdapter turning open LLM endpoints into Jev-compatible classification services without training a separate classifier head.What Jev does here Extracts log-probabilities of candidate tokens from model vocabulary logits, formatting them into standard Jev responses.
• agentjido/req_llmToolingGitHub ↗★ 602ElixirA TypeSafe provider for calling Jev through ReqLLM’s evaluate interface in Elixir.What Jev does here Sends state and questions, normalizes answers and retains the raw provider response.
• BillionsBobby/JevRouterToolingGitHub ↗★ 466—Routes among models, subagents, skills, MCP tools and CLIs using a shared candidate set.What Jev does here Jev makes a Choice; the router separately checks availability, permissions, risk and confirmation policy.
• notque/vexjoy-agentToolingGitHub ↗★ 444PythonAn optional Jev routing path that matches VexJoy requests to specialist Agents, skills and workflows.What Jev does here After deterministic routing guards, Jev judges the remaining candidates and required workflow components.
• WrongStack/WrongStackToolingGitHub ↗★ 401TypeScriptAn optional Jev dispatch classifier for choosing among WrongStack specialist Agents.What Jev does here Jev evaluates the task against eligible specialists; local dispatch rules use the result.
• cognesy/instructor-phpToolingGitHub ↗★ 328PHPA TypeSafe Decision driver within Instructor PHP’s Polyglot module.What Jev does here Converts application state and typed questions into Jev requests and maps responses to PHP decision objects.
• monotykamary/pi-fabricToolingGitHub ↗★ 320TypeScriptPi’s programmable runtime includes an optional Jev loop for observing state, making decisions and running bounded actions.What Jev does here Programmed questions feed Jev judgments into local action logic under runtime budgets.
• typesafe-ai/typesafe-sdk-pythonToolingGitHub ↗★ 307PythonOfficial TypeSafe Python SDK with synchronous and asynchronous clients for Jev System One, plus question and answer types.What Jev does here system_one sends context and choice, score or yes/no questions to the API, then parses answers by question name.
• yonatangross/orchestkitToolingGitHub ↗★ 300TypeScriptOrchestKit can optionally use Jev to classify coding sessions and set their colors when confidence meets a threshold.What Jev does here Classifies the first task prompt and branch state by work type; local policy accepts the result or falls back.
• typesafe-ai/typesafe-sdk-jsToolingGitHub ↗★ 285TypeScriptThe JavaScript and TypeScript SDK published by TypeSafe, with typed Jev requests and answers.What Jev does here systemOne submits state and named questions and infers answer types from the questions.
• kitze/skillboxToolingGitHub ↗★ 277TypeScriptA self-hosted, versioned Agent skills library with optional Jev recommendations.What Jev does here Jev scores task relevance among skills the client is allowed to access.
• 0xNatoshi/jev-codex-routerToolingGitHub ↗★ 275PythonUses Jev to classify each Codex turn, then applies local rules to choose the model, reasoning effort, and speed mode.What Jev does here Classifies task difficulty and reasoning needs before local policy selects a model configuration.
• monteduro/killmyideaToolingGitHub ↗★ 272TypeScriptA startup-idea evaluation demo assigning KILL, FIX or SHIP labels from Jev scores.What Jev does here Jev answers scoring, category and clarity questions; local weights and gates calculate the final label.
• cequence-io/openai-scala-clientToolingGitHub ↗★ 257ScalaA dedicated TypeSafe module in a Scala client that supports multiple AI providers.What Jev does here Sends shared state and typed questions to Jev and parses structured answers.
• NiazMorshed2007/jev-reviewToolingGitHub ↗★ 248TypeScriptA local MCP code-quality reviewer returning structured scores to coding Agents.What Jev does here Jev scores correctness, complexity, tests and security; code ranks areas to improve.
• danieljvdm/effect-agentToolingGitHub ↗★ 177TypeScriptAn Effect Agent TypeSafe decision provider for typed question sets and optional model selection.What Jev does here Jev answers probability, choice and score questions for application transitions or model selection.
• tamaratran/jev-prunerToolingGitHub ↗★ 166TypeScriptA Claude Code output-pruning plugin filtering selected Bash output before it reaches the main model.What Jev does here After length and content checks, Jev judges which chunks to retain while original output is archived.
• Michaelliv/runlineToolingGitHub ↗★ 165TypeScriptA TypeSafe plugin exposing Jev decisions as callable actions in Runline Agent JavaScript.What Jev does here evaluate, choice, score and noul actions submit questions and retain answers and usage.
• supercorp-ai/supercovToolingGitHub ↗★ 159—A quality and coverage CLI for coding agents: Jev assesses source properties while local coverage highlights testing targets.What Jev does here Asks Jev about file-quality properties; code composes scores and ordering.
• ldbumble/taskuaryToolingGitHub ↗★ 143PythonAn optional Jev judgment module in Taskuary for checking user-defined conditions on task state.What Jev does here Turns conditions into yes/no probability questions and returns local-threshold verdicts plus probabilities.
• hackclub/aiToolingGitHub ↗★ 142TypeScriptA Jev forwarding endpoint in the Hack Club AI proxy, using its authentication, limits and usage logging.What Jev does here Forwards authorized structured requests to TypeSafe and returns answers with usage accounting.
• mrnugget/jev-shell-historyToolingGitHub ↗★ 119TypeScriptFish-style Zsh history suggestion tool ranked by Jev, ordering candidate commands from local history based on context.What Jev does here Packages current command input and historical candidates into a Jev request, ranking the most plausible command for inline suggestion.
• GhalebDweikat/winnowToolingGitHub ↗★ 115PythonA context filter for Claude Code that hides irrelevant tool-output blocks and keeps the original text available for recall.What Jev does here Jev scores whether Read, Bash and Grep output blocks are needed; local thresholds keep relevant or uncertain blocks.
• rokcso/bluenoiseToolingGitHub ↗★ 94TypeScriptAn X/Twitter filtering extension using local rules by default, with optional Jev checks for unmatched replies.What Jev does here When experimental AI is enabled, Jev evaluates replies missed by rules and local thresholds decide whether to hide them.
• mizchi/jev-playgroundToolingGitHub ↗★ 73TypeScriptA MoonBit and TypeScript Jev playground covering games, browsers, command risk and small languages.What Jev does here Experiments send action candidates or typed questions to Jev, then execute or record the answers.
• obie/ruby_decision_modelToolingGitHub ↗★ 59RubyA Ruby decision-model client for Jev through TypeSafe’s native API or OpenRouter.What Jev does here A shared Client sends state and typed questions and parses choices, probabilities, scores and usage.
• yusukebe/hono-jev-routerToolingGitHub ↗★ 52TypeScriptAn experimental semantic HTTP router for Hono using natural-language route descriptions.What Jev does here Jev scores request-to-description matches; code selects the first route above its threshold.
• hotchpotch/jev-rerankerToolingGitHub ↗★ 50PythonJev-powered relevance filtering and reranking for RAG in Python.
• alp82/goodwatch-monorepoToolingGitHub ↗★ 50PythonA film-and-TV attribute-scoring experiment inside GoodWatch comparing Jev question designs and batch sizes.What Jev does here Asks whether predefined traits are present or how strongly they appear, recording scores, latency and Token usage.
• shiftynick/jev-axiToolingGitHub ↗★ 46TypeScriptA CLI for Jev pick, rate, check, rank, triage, and guard tasks, with optional hooks before Agent tool calls.What Jev does here Converts input state and options into structured questions, returning results or risk scores for local policy.
• nexibeo/jev-cookbookToolingGitHub ↗★ 39JavaScriptPractical, tested recipes for TypeSafe's Jev decision model on OpenRouter: support triage, database indexing, file organizing, tagging, taxonomies, dedupe, PII detection, extraction, search re-ranking and a browser agent.
• iammrduncan/typesafe-ai-benchmarkToolingGitHub ↗★ 38TypeScriptCompares Jev with other structured-output models on shared application tasks, recording errors, latency, Tokens, and estimated cost.What Jev does here Maps the same tasks to Jev Choice/Noul questions and normalizes answers to a shared result format.
• GodsBoy/jev-agent-skill-routerToolingGitHub ↗★ 31PythonTyped, confidence-aware agent skill routing with TypeSafe Jev.
• wundercorp/lokiToolingGitHub ↗★ 28PythonLoki optionally adds Jev typed-judgment tools and routes a new session to a model within the selected gateway.What Jev does here Assesses the first task’s capability needs; local policy chooses a same-gateway model and keeps the route sticky.
• tumf/jev-cliToolingGitHub ↗★ 19PythonA CLI and stdio MCP server for typed Jev judgments over text or JSON.What Jev does here Submits noul, choice and score questions and emits JSON or a primary value.
• kieranklaassen/ruby_llm-typesafeToolingGitHub ↗★ 19RubyA TypeSafe provider for RubyLLM 2 that exposes Jev’s three judgment types through structured output.What Jev does here Builds Noul, Choice and Score questions with Schema and returns answers to the RubyLLM application.
• mejiasd3v/pi-jev-routerToolingGitHub ↗★ 17JavaScriptAutomatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway
• kavehmz/typesafe-playgroundToolingGitHub ↗★ 15JavaScriptInteractive Jev experiments for support-routing previews and 3D driving simulations.What Jev does here Judges support messages or chooses lanes and target speed from structured simulated sensors.
• prismhq/jev-routerToolingGitHub ↗★ 15PythonOpen-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM
• Kevthetech143/super-jevToolingGitHub ↗★ 14PythonA TypeScript decision-to-action harness connecting evidence, Jev judgments, permitted actions, and outcome records.What Jev does here Submits typed questions, validates answers, and lets domain rules choose registered tools with permission and argument checks.
• bohutang/siftToolingGitHub ↗★ 13JavaScriptChrome extension that labels every post on X (Substance · Humor · Chit-chat · Promo · Junk · AI-written) with TypeSafe Jev, and hides the ones you don't want.
• doeixd/jev-prefToolingGitHub ↗★ 13JavaScriptTurns AGENTS.md preferences into rules checked by Jev against hunks, staged files or PRs.What Jev does here Jev classifies change evidence against configured rules; code maps answers to review outcomes.
• matthewp/flue-jev-demoToolingGitHub ↗★ 11TypeScriptFlue agent routing with TypeSafe Jev through Cloudflare AI Gateway
• frostney/clean-code-reviewToolingGitHub ↗★ 11TypeScriptEvery code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.
• MarissaFamularo/citation-verifierToolingGitHub ↗★ 11JavaScriptCheck whether each cited paper supports the sentence citing it. Claude proves the quote, TypeSafe's Jev scores it, a human decides.
• abhixhek/jevcalToolingGitHub ↗★ 10PythonA toolkit for evaluating Jev probabilities on labeled data, selecting confidence thresholds and checking model drift.What Jev does here Runs fixed questions and measures accuracy, calibration, coverage and escalation rates.
• gtaras7/typesafe-jevToolingGitHub ↗★ 10TypeScriptScreen a folder of CVs with the TypeSafe Jev decision model: typed judgments, an editable policy, free re-scoring.
• adarshmishra07/jcm-routerToolingGitHub ↗★ 8TypeScriptLocal proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone.
• valentynkit/jev.nvimToolingGitHub ↗★ 8LuaNeovim: ask the buffer a question, get a quickfix list. Treesitter splits functions, Jev scores each one, probabilities land as virtual textWhat Jev does here Scores each Treesitter function against the user question, splitting across requests if the buffer does not fit. Every hit is listed in quickfix; only hits at or above the threshold get buffer marks.
• raihankhan-rk/diffjuryToolingGitHub ↗★ 7TypeScriptDiffJury — TypeSafe Jev PR risk router + code review coach
• kitze/pagegradeToolingGitHub ↗★ 7TypeScriptGrade page sections for clarity, writing and on-page SEO. WXT + TypeSafe AI Jev.
• kuhung/understanding-jevToolingGitHub ↗★ 6HTMLReading Jev: a deep dive into its millisecond judgments and engineering limits.
• FFatTiger/new-api-plugin-typesafeToolingGitHub ↗★ 4JavaScriptTypeSafe AI System One (Jev) task plugin for QuantumNous/new-api — native /v1/systemone, synchronous evaluation, token billing
• cephalization/jev-triageToolingGitHub ↗★ 4TypeScriptUses typeful jev, zero sync to pull and sync large repositories for issue triage
• Butochnikov/laravel-typesafe-jevToolingGitHub ↗★ 3PHPA Laravel adapter for Jev with configuration, dependency injection, a Facade and a request-recording test fake.What Jev does here Wraps a community PHP SDK for typed judgments and preserves promises and exceptions.
• komikat/jev-bfsToolingGitHub ↗★ 1PythonWikipedia link races with direct Jev ranking and a live terminal display.

No matching projects.

Snapshot taken 2026-11-02; star counts drift over time.