jevland

REPOSITORY ACTIVITY

Latest pushes

Latest repository pushes from our saved GitHub snapshot. Each repository has its own metadata check time; the list changes when that snapshot is refreshed.

398repositories with a recorded push
404indexed repository addresses

2 redirected addresses are merged into their current repositories. 4 repositories have no usable push metadata in this snapshot. Browse all repositories → · Activity JSON

398 repositories, ordered by last push.

  1. integrationsource-backed

    pydantic/pydantic-ai

    Pydantic AI merged a TypeSafe model provider: `TypeSafeModel('jev-latest')` with confidence thresholds, a FileUnderstanding capability and fallback to an LLM for tool calls; docs cover jev-latest, jev-preview and pinned releases.

    Pydantic AI: first-class TypeSafeModel →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 21,267 stars
  2. integrationsource-backed

    lidge-jun/opencodex

    OpenCodex adds Jev decision services to its provider and combo-routing system. Optional automatic routing chooses a configured model and reasoning effort before the main coding request.

    OpenCodex: Jev model routing →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 18,625 stars
  3. integrationsource-backed

    genspark-ai/genoffice

    A desktop office suite indexes local document text in SQLite and can use Jev to reorder search results. The optional reranker evaluates candidate files against the search question before showing the ranked list.

    GenOffice: Jev file-search ranking →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 12,568 stars
  4. integrationsource-backed

    Wei-Shaw/sub2api

    A self-hosted API gateway forwards Jev requests through the native System One endpoint and manages TypeSafe API-key accounts. Choice, Noul and Score answers keep their structured response format.

    Sub2API: native System One gateway →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Go · 46,231 stars
  5. directorysource-backed

    hellogumbo/awesome-jev

    A large, actively maintained community directory of SDKs, integrations, agent tools, games, demos and research.

    Awesome Jev →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    JavaScript · 226 stars
  6. integrationsource-backed

    ComposioHQ/composio

    Composio includes a TypeSafe provider for selecting tools and binding arguments with explicit choices. Its implementation separates closed argument sets from values that require an open-ended companion model.

    Composio: TypeSafe tool decisions →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 31,157 stars
  7. integrationsource-backed

    Paca-AI/paca

    Paca adds per-project Jev decisions for agent selection, task assignment and filling supported empty task fields. Automation conditions can branch on typed answers while keeping human-set values intact.

    Paca: Jev project and task routing →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Go · 2,080 stars
  8. reposource-backed

    run-llama/liteparse

    An OSS library from the LlamaIndex founder: give a document plus natural-language category rules and Jev predicts the category (classify) or the boundaries between sub-documents (split). OCR backends: liteparse (fast, free) or LlamaParse for complex layouts.

    DocJev: document classification and splitting with Jev →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Rust · 13,064 stars
  9. integrationsource-backed

    CopilotKit/openfuse

    OpenMuse represents Jev decisions as interactive controls inside its assistant interface. Server adapters and shared schemas connect typed answers with selectable actions and human review.

    OpenMuse: Jev decision controls →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 6,519 stars
  10. replicasource-backed

    SimpleJev/JevAny

    A training and deployment library adapts language-model backbones to typed decisions with learned pointer heads or direct option-token readouts. It publishes LoRA checkpoints, data preparation, calibration and evaluation tools alongside an archived application replay gallery.

    JevAny: train and deploy decision models across backbones →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 138 stars
  11. integrationsource-backed

    LLPhant/LLPhant

    LLPhant exposes Jev through a PHP classifier and typed request objects. Applications can send a state with classification questions through the native TypeSafe endpoint.

    LLPhant: PHP Jev classifier →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    PHP · 1,721 stars
  12. replicasource-backed

    daseinlabs/open-jev

    One-pass option scoring with a local Gemma 3 4B via MLX: pre-written options are batched against a cached context; implements the System One API contract and includes a Doom terminal demo.

    open-jev (MLX, Apple silicon) →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 138 stars
  13. integrationsource-backed

    mattt/AnyDecisionModel

    A Swift package offers typed probabilities, enum choices and ordinal scores through a model-and-session interface. It can call TypeSafe Jev or a compatible local server, and an optional MLX backend reads local model token probabilities without generating text.

    AnyDecisionModel: typed decisions from Swift sessions →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Swift · 61 stars
  14. integrationsource-backed

    AgentiLoop/Agent

    The macOS Agent! application can ask Jev for advisory judgments about its planned actions. A Swift middleware layer defines the questions and converts returned verdicts into application decisions.

    Agent!: optional Jev action advisor →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Swift · 656 stars
  15. replicasource-backed

    jaredpalmer/kev

    A family of tiny Jev-like decision models — 0.5B at launch, now 0.6B, 4B and 8B on Qwen3.5 — using the same LoRA-plus-pointer-head recipe with block-causal masking so questions run in parallel; the HTTP API mirrors System One, so the official SDK works with only a base_url change.

    kev: a tiny Jev-like you can train on a MacBook →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 10,040 stars
  16. reposource-backed

    lirantal/discoprint

    A command-line tool fetches an artist's discography and lyrics, asks Jev for theme, mood and lyrical-complexity judgments, and displays the results in a terminal dashboard. Saved classification files can be rendered again without new model calls.

    Discoprint: a classified discography in the terminal →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    JavaScript · 4 stars
  17. repoofficial

    typesafe-ai/system-one-adapter-python

    A drop-in replacement for the TypeSafe client that answers the same state-plus-questions contract with an ordinary LLM API, useful for comparing Jev against OpenAI- or Anthropic-compatible models on identical calls.

    System One adapter for LLM APIs →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 410 stars
  18. integrationsource-backed

    kerpopule/hermes-jev-skills

    Jev-powered model routing, memory, context compaction, skill selection and computer/browser use for Hermes agents (also Claude Code and Codex), with a routing dashboard and shadow mode that shows what Jev routing would have saved before you switch it on.

    hermes-jev-skills: routing, memory, compaction, GUI clicks for Hermes →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 1,350 stars
  19. directorysource-backed

    cobanov/awesome-jev

    A source-backed list of 70+ Jev projects in eight categories, including open reproductions and evaluations; reviewed 2026-09-18 per its README.

    cobanov/awesome-jev →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Language not recorded · 600 stars
  20. reposource-backed

    jkudish/jev-mcp

    A proof-of-concept MCP server exposing three tools: verify a claim against evidence, screen text for injection or relevance, and rank candidates semantically.

    jev-mcp →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    JavaScript · 584 stars
  21. integrationsource-backed

    yusukebe/hono-jev-router

    An experimental semantic router for Hono by its creator: routes are described in plain language and Jev matches incoming requests to them from method, URL, headers and body.

    hono-jev-router →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 54 stars
  22. replicasource-backed

    featherless-ai/simple-jev

    SimpleJev.ai from Featherless: a fully open-source library that takes any Hugging Face model and 'Jev-ifies' it behind an API endpoint, with public no-key endpoints, vision via chat-format images (Gemma, Qwen) and an RFDT tuning recipe to distil your prompts into a smaller production model.

    simple-jev →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 660 stars
  23. repoofficial

    typesafe-ai/typesafe-sdk-python

    The official Python client (`uv add typesafe-sdk`) with sync and async variants; the quickstart classifies support tickets into billing, technical or other.

    typesafe-sdk (Python) →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 315 stars
  24. reposource-backed

    openlayer-ai/jevals

    An evaluation library expresses agent, quality and security checks as typed questions and packs compatible checks into shared decision requests. The same definitions can measure recorded traces or gate an agent step, using hosted Jev or supported local decision engines.

    Openlayer jevals: batched decision-model evaluations and guardrails →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 120 stars
  25. reposource-backed

    superagents-lab/jev-search

    Jev chooses sources and query settings, then re-ranks results returned by search engines. It does not generate an answer.

    Jev Search →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 562 stars
  26. benchmarksource-backed

    chepyle/jev-test

    A reproducible zero-shot evaluation freezes the LexGLUE test splits and maps legal classification tasks to Choice or per-label Noul questions. Its runner saves completed requests, checks model-version changes and writes micro/macro-F1, calibration, usage and cost reports.

    Jev × LexGLUE: typed decisions across seven legal tasks →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 0 stars
  27. integrationsource-backed

    yzfly/edgejev

    A deployment toolkit exports compatible open decision scorers to ONNX, quantizes them and serves the TypeSafe request format locally. It preserves upstream readouts and calibration settings while exposing accuracy and precision trade-offs for CPU deployment.

    EdgeJev: export and quantize decision models for CPU →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 42 stars
  28. replicasource-backed

    malevrigns/agent-jev

    A Qwen3-0.6B backbone with its language-model head removed scores caller-supplied candidates through a permutation-equivariant head. The project releases training, serving and prefix-sharing code for Boolean, Choice and Score decisions, including a coding-completion checkpoint.

    AgentJev: a small candidate-head model for agent decisions →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 368 stars
  29. integrationsource-backed

    kitze/unclutter

    A WXT browser extension that asks Jev whether page elements are clutter (ads, cookie banners, upsells), then saves reusable per-template hiding rules; sends snippets rather than full pages, bring your own key.

    Unclutter: Jev-powered clutter blocker →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 395 stars
  30. integrationsource-backed

    burnigtm/jev-mcp

    A local MCP server gives coding agents Jev judgments for loop routing, patch review, evidence checks and candidate ranking. Its prepared-call router selects an exact host-supplied tool call while retaining the original arguments locally.

    burnigtm Jev MCP: exact prepared call routing →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 68 stars
  31. repoofficial

    typesafe-ai/skills

    TypeSafe's public skills repository with the `typesafe-ai` SKILL.md used by Claude Code, Codex and other agent environments to design bounded Jev decisions.

    Official agent skills repository →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Language not recorded · 2,905 stars
  32. reposource-backed

    bartlomein/oko

    A local Rust search tool combines keyword discovery with Jev ranking and delivers source excerpts through a CLI or MCP. Its setup command connects Codex, Claude Code and OpenCode and can supply retrieval context when a code question is submitted.

    Oko: local code search and prompt-time retrieval →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Rust · 13 stars
  33. replicasource-backedarchived

    wfzyx/von

    `pip install von`: a non-autoregressive local decision model claiming wire-protocol compatibility with Jev (`von serve`), with ModernBERT or Laya-421M backends; Apache-2.0.

    von: a CPU-only local decision model →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 922 stars
  34. replicasource-backed

    feder-cr/jev

    A native CPU server serves an independent decision model through the TypeSafe wire format. Yes/no predictions are also composed into option distributions and ordered scores, with shared-state reuse and packaged OpenVINO or GGUF weights.

    jevos: TypeSafe-compatible decisions on a laptop CPU →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    C++ · 971 stars
  35. replicasource-backed

    TianyuCodings/NanoJev

    A 0.6B Qwen-based open implementation of parallel typed decisions, with training and evaluation code.

    NanoJev →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 2,602 stars
  36. reposource-backed

    suraj-phanindra/wellposed

    An offline linter checks Jev request design before inference, including missing escape options, broken state references and malformed criteria. An optional semantic layer asks Jev whether a structurally valid question has missing or ambiguous answer boundaries.

    wellposed: lint the structure and meaning of Jev questions →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    JavaScript · 2 stars
  37. roundupcommentary

    ranjan2829/AskJev

    A Chinese X Article sorting the early ecosystem into things that actually ship: jev-ultrafast, mobile-jev, typesafe-computer-use, AskJev, a Twitter timeline analyzer, a tax-document classifier, jevdetector and newsjack, plus the OpenRouter and DataCamp explainers.

    Got Jev — now what? A real deployment list →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 8 stars
  38. reposource-backed

    realZachi/pg-jev

    A PostgreSQL extension that exposes Jev-backed categorical judgments over table rows.

    pg-jev →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Shell · 1,313 stars
  39. replicasource-backed

    Zefan-Cai/Open-Jev

    An independent family of LoRA adapters and scalar decision heads returns Choice, Noul and Score outputs over pinned Qwen backbones. The project publishes training data, evaluation records, a CPU classification workbench and interactive saved-decision replays.

    Open-Jev: trained decision heads and an inspectable replay workbench →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 452 stars
  40. replicasource-backed

    caiovicentino/eikos

    A family of open 4B and 27B models applies stated rules and policies through typed option probabilities. The repository includes data generation, distillation, quantization, evaluation and a TypeSafe-compatible server, with GPU and Apple Silicon builds.

    Eikos: open typed decisions for financial rules →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 43 stars
  41. replicasource-backedarchived

    ekzhang/openjev-sglang

    A server that implements the TypeSafe/Jev HTTP API on Qwen3.6-35B-A3B with SGLang: prefill-only, one extra token per question, radix caching, deployable on Modal.

    openjev-sglang →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 334 stars
  42. benchmarksource-backed

    blowxian/jev-fanout-bench

    A measurement harness compares many typed questions in one Jev request with the same questions asked separately. It varies state size and question count, repeats requests to estimate noise and publishes response-level usage, billing and latency evidence.

    jev-fanout-bench: measure batching, billing and answer stability →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 0 stars
  43. roundupcommentary

    kyotofin/tax-doc-classifier

    A Chinese X Article sorting the early ecosystem into things that actually ship: jev-ultrafast, mobile-jev, typesafe-computer-use, AskJev, a Twitter timeline analyzer, a tax-document classifier, jevdetector and newsjack, plus the OpenRouter and DataCamp explainers.

    Got Jev — now what? A real deployment list →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 521 stars
  44. integrationsource-backed

    Bodila51/grok-bot-jev

    A seven-step setup that puts Jev between Grok Bot and its actions: a jev-usage-router skill is consulted before browser, research, retry or extra-bot steps; it starts in shadow mode with logs, then goes active, with a kill switch. Repository included.

    Jev as a decision layer for Grok Bot →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 133 stars
  45. reposource-backed

    jeffclimbsbikes/system-one-playground

    A local workbench runs open decision engines side by side and can compare them with hosted Jev. It includes a visual request builder, dataset benchmarks, truncation diagnostics and resource or concurrency measurements with separate engine processes.

    System One Playground: compare decision engines on Apple Silicon →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 0 stars
  46. demosource-backed

    lykycy123/RoboJEV

    A Franka Panda simulator separates Jev's choice of manipulation intent from its choice of movement and gripper commands. A local executor applies those commands, and independent physical checks determine whether a task succeeded.

    RoboJEV: two-stage control in MuJoCo →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 64 stars
  47. reposource-backed

    EliaAlberti/jev-rules

    A Claude Code plugin that asks Jev which standing rules and codebase maps are relevant to the current prompt or file edit, injects only those, and falls back to all rules if the API is down.

    jev-rules for Claude Code →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    JavaScript · 65 stars
  48. reposource-backed

    jerryjliu/docjev

    An OSS library from the LlamaIndex founder: give a document plus natural-language category rules and Jev predicts the category (classify) or the boundaries between sub-documents (split). OCR backends: liteparse (fast, free) or LlamaParse for complex layouts.

    DocJev: document classification and splitting with Jev →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 563 stars
  49. benchmarksource-backed

    anessbelbati/jev-rerank-bench

    A retrieval study compares typed Jev scoring strategies with dedicated rerankers and open-model controls on the same passage candidates. Saved provider responses, query-level evidence, bootstrap intervals and an interactive viewer support inspecting each result.

    Jev reranking: saved outputs across retrieval tasks and scoring strategies →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 11 stars
  50. benchmarksource-backed

    KantaHayashiAI/jev-does-not-play-dice

    An independent experiment compares Jev's reported probabilities with known uncertainty on fair dice, coins and option sets. It also tests whether typed decisions preserve probabilities stated in forecast documents, publishing recorded outputs and offline analysis scripts.

    Jev Does Not Play Dice: inspect probabilities on known uncertainty →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    JavaScript · 4 stars
  51. benchmarkauthor demo

    Zaious/jev-capability-atlas

    A bilingual (Traditional Chinese / English) evidence map of where Jev holds up and where it breaks, with API-call receipts under suites/. Its thesis: success tracks whether the answer is derivable from the supplied state rather than from outside knowledge.

    Jev capability atlas →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 30 stars
  52. demosource-backed

    carlaiau/read-with-jev

    A classic-novel reader adds Jev's whole-sentence emotion associations alongside a deterministic character map. Readers can adjust which emotion scores are highlighted and explore nearby text without changing the original novel.

    Read with Jev: an emotion-aware novel reader →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 3 stars
  53. demosource-backed

    anishfn/shapeshift

    A text box switches among predefined cards for events, timers, lists, calculations and other intents. Jev classifies the intent and supporting signals while deterministic parsers extract values and a confidence-based state machine controls when the interface changes.

    Shapeshift: text input that becomes a useful interface →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 1,076 stars
  54. reposource-backed

    spoonnotfound/soupbase

    A bilingual puzzle application where Jev classifies player questions and judges proposed explanations through typed outputs. It includes hints, private puzzle authoring, revocable share links and configurable TypeSafe, OpenRouter or Vercel AI Gateway access.

    Soupbase: bilingual lateral-thinking puzzles judged by Jev →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 9 stars
  55. demosource-backed

    FBddcz/embodied-jev

    A MuJoCo robot workbench compares bounded skills, incremental movement and hierarchical control on manipulation tasks. It exposes decision traces, physical checks and alternative providers, including Jev, compatible chat models and a local MiniCPM model.

    EmbodiedJev: an inspectable robot decision workbench →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 342 stars
  56. demosource-backed

    enoyola/jev-grand-prix

    A local racing game asks Jev to choose the racing line, pedal input and whether the car is in trouble. Browser physics follows the chosen line, while recorded corner performance informs bounded speed adjustments for the next lap.

    Jev Grand Prix: racing lines and pedals →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    JavaScript · 7 stars
  57. benchmarksource-backed

    marcosmartinez/jev-acento

    A preregistered audit compares English and Spanish state and instruction combinations for Jev on paired human-labelled datasets. The repository publishes the runner, frozen prompts, response-derived results and a CLI for repeating the protocol on other labelled data.

    jev-acento: a paired Spanish-language accuracy and calibration audit →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 0 stars
  58. integrationsource-backed

    limboinf/semantic-live-caption

    A Chinese and English caption interface combines streaming speech recognition with Jev judgments for important statements, emotion and communicative intent. Partial captions receive provisional annotations, followed by another judgment when the sentence closes.

    Semantic Live Caption: annotate a speech transcript →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    HTML · 11 stars
  59. demoauthor demo

    0xtrou/rubikjev

    Scramble a Rubik's cube and watch Jev judge and solve it live, with difficulty tiers, XP and token-metered runs; labelled experimental and fan-made.

    Jev solves the cube →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 7 stars
  60. demosource-backed

    andrewsilber/JevsBistro

    A deterministic restaurant simulator that replays the same seeded dinner under rule-based, camera-assisted and Jev-planned service. Servers choose from feasible task tours, and the app logs the observations, candidates, confidence, latency and resulting service metrics.

    JevsBistro: replayable restaurant service decisions →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 3 stars
  61. demosource-backed

    marc2332/findme

    'jev, find me stuff in my system' — a file finder that asks Jev which files match a natural-language request.

    findme: jev + fs →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Rust · 26 stars
  62. reposource-backed

    rimusz/jev-mcp

    A proof-of-concept MCP server exposing three tools: verify a claim against evidence, screen text for injection or relevance, and rank candidates semantically.

    jev-mcp →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 0 stars
  63. productsource-backed

    0xArx/jevegis

    A bring-your-own-key API with /v1/scan (prompt injection, jailbreak, credential leaks) and /v1/moderate (nine categories) returning calibrated probabilities; free tier live.

    Jevegis: guardrails API on Jev →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 3 stars
  64. demosource-backed

    jexp/neo4jev

    Outgoing relationships become choices, Jev returns next-hop probabilities, and a beam search walks the graph; shipped as a library, notebooks and a Streamlit app on Neo4j's public Companies knowledge graph.

    neo4jev: graph navigation with Jev →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Jupyter Notebook · 189 stars
  65. replicasource-backed

    kikoncuo/jevfire

    An independent CUDA runtime scores verified single-token option labels with existing language-model weights. It batches independent fields through vLLM, reuses shared prefixes when supported and assembles typed output in code; browser experiments also use local WebGPU models.

    JEVfire: parallel finite-choice decisions with vLLM →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    JavaScript · 77 stars
  66. integrationsource-backed

    colliber/duckdb-jev

    A DuckDB extension with jev_choice(), jev_score(), jev_noul() and jev_ask() returning real SQL types, batching 16 rows per request and caching identical queries.

    duckdb-jev →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    C++ · 35 stars
  67. integrationsource-backed

    reycn/smart-switch

    A native Mac switcher asks Jev which running app the user is likely to open next. A Rust core supplies recent activation and dwell-time history, while a Swift menu-bar app executes the selected app activation and exposes the request and response.

    SmartSwitch: predict the next Mac app →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Swift · 3 stars
  68. reposource-backed

    abhixhek/jevcal

    A CLI evaluates Jev against labelled application data, chooses per-question thresholds on one split and checks them on held-out examples. It writes a threshold lock and report, supports low-confidence fallback, and fails CI when accepted accuracy or coverage drifts.

    jevcal: fit confidence thresholds and detect decision drift →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 12 stars
  69. replicasource-backed

    akash-kamat/system-one-gemma

    Reimplements a System One decision model on Gemma 3 270M with a LoRA of 2.6M trainable parameters, scoring all options in one forward pass; trains in a free Colab and ships weights in the repo.

    system-one-gemma →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 8 stars
  70. demoauthor demo

    JacobLinCool/jev-paper-judge

    Upload a research-paper PDF; text is extracted in the browser, split into roughly 1,000-word passages, and a fixed set of small questions is asked per passage in parallel, then combined into weighted scores.

    Jev Paper Judge →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 1 stars
  71. reposource-backed

    caiovicentino/jev-shield

    Sits between MCP clients and servers with three layers: structural allowlists, semantic hazard detection via Jev, and session taint tracking; targets poisoned tool descriptions, injection, exfiltration and secrets.

    jev-shield: semantic MCP firewall →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    JavaScript · 4 stars
  72. roundupcommentary

    altryne/twitter-timeline-analyzer

    A Chinese X Article sorting the early ecosystem into things that actually ship: jev-ultrafast, mobile-jev, typesafe-computer-use, AskJev, a Twitter timeline analyzer, a tax-document classifier, jevdetector and newsjack, plus the OpenRouter and DataCamp explainers.

    Got Jev — now what? A real deployment list →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    JavaScript · 2 stars
  73. integrationauthor demoarchived

    zsoXi/agent-handoff-gate

    An experimental protocol where a worker agent sends requirements, code and test results to Jev, which returns an evidence verdict for the team-lead agent before results are accepted.

    Agent Handoff Gate →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 0 stars
  74. demosource-backed

    lbotinelly/jev-little-airways

    A small archipelago flight simulation that asks Jev about diversion, emergency broadcasts, traffic response and approach clearance. A tower decision orders waiting aircraft, while ordinary code enforces runway occupancy and the monitor exposes API exchanges and usage.

    Little Airways: aircraft and tower judgments in a toy airspace →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    HTML · 6 stars
  75. demosource-backed

    lukaske/jev-doom-agent

    A browser-native experiment compares Jev control with a labelled local policy using isolated Chocolate Doom WebAssembly engines. Jev chooses movement, view, firing and interaction controls from structured spatial state, and local code executes those controls.

    PROMPT FPS: browser-native Doom control →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    TypeScript · 36 stars
  76. benchmarksource-backed

    AbdelStark/jev-benchmarks

    A framework comparing hosted Jev with a local GLiNER2.5 on zero-shot single-label classification (AG News, Banking77, DAIR Emotion) for accuracy, calibration, selective-automation coverage and latency, with bootstrap intervals.

    Jev vs GLiNER2.5 benchmark →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 28 stars
  77. replicasource-backed

    mithalouni/system-one-open

    An open replica trained on 92 public datasets plus synthetic generators, on Gemma 4 E2B (LoRA) and Gemma 3 270M, served via FastAPI on Modal with a live demo.

    system-one-open →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 41 stars
  78. integrationsource-backed

    prismhq/jev-router

    An OpenAI-compatible router that uses Jev to pick a model on top of LiteLLM, filtering candidates by capability and falling back to the cheapest model without a TypeSafe key.

    jev-router on LiteLLM →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 15 stars
  79. replicasource-backed

    vinnylarouge/jevlike

    An early independent implementation of a Jev-style interface on an open model; cited as inspiration by daseinlabs/open-jev.

    jevlike →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 1,371 stars
  80. demosource-backed

    phyous/tsai-sc

    A harness for the original StarCraft shareware campaign that gives Jev structured visible game state and executes its choices through keyboard and mouse inputs. The release includes a probability-overlay video and an inspectable run bundle.

    Jev plays StarCraft: a recorded Strongarm mission →
    Last push
    Metadata checked
    Metadata status
    ok
    Repository
    Python · 28 stars

Last push records repository activity across branches and tags. Release announcements and descriptions of individual changes need their own sources. Dates are shown in UTC; “Metadata checked” belongs to that repository alone.