Skip to content
Made with Jev

Tools that run on Jev

Apps, agents and dev tools with Jev under the hood. Find one to try, or see what others ship with it.

List yours for $5
  1. jevgate logo

    jevgate (opens in a new tab)

    SDKs and integrations

    Gate a shell command on a yes/no answer from Jev. Smarter cron.

    github.com/gordonbrander/jevgate

  2. brojev logo

    brojev (opens in a new tab)

    Agents and browsers

    A Jev browser agent for Claude Code. One Go binary, no Playwright.

    github.com/barockok/brojev

  3. pi-skimmer logo

    Jev keeps the relevant chunks of text and JSON for the Pi coding agent.

    github.com/jon-devlapaz/pi-skimmer

  4. Jeva logo

    A System One model built from first principles, with open weights.

    github.com/LiQiiiii/Jeva

  5. gallant logo

    gallant (opens in a new tab)

    Coding and code review

    A customizable linter that asks a decision model your fuzzy rules.

    github.com/madxmike/gallant

  6. DeciLabel logo

    DeciLabel (opens in a new tab)

    Coding and code review

    A GitHub Action that labels issues and pull requests with a decision model.

    github.com/EvanProgramming/decilabel

  7. Dex logo

    An open-source, Jev-compatible decision model on an Ettin-1B encoder.

    github.com/CanadaOrNaw/dex

  8. LevelDez logo

    A 3D interior level designer where a yes/no model presses the buttons.

    github.com/yeme-oss/LevelDez

  9. JevRouter logo

    JevRouter (opens in a new tab)

    Routing and model choice

    One typed Choice question picks the model, tool or subagent.

    github.com/BillionsBobby/JevRouter

  10. mu logo

    mu (opens in a new tab)

    Context and memory

    A coding agent where a small judge makes the routine calls.

    github.com/qybaihe/mu

  11. Jevlint logo

    Jevlint (opens in a new tab)

    Coding and code review

    A linter that checks code against plain-language rules.

    github.com/codegirl-007/jevlint

  12. Julia 1 logo

    A 144.3M-parameter decision model that edges Jev on typed decisions.

    huggingface.co/SupersonicLabs/Julia-1

  13. Jeff 1 logo

    An open typed-decision model with a guide to training your own.

    huggingface.co/GestaltLabs/Jeff-1

  14. stuntd logo

    A local proxy that answers typed LLM decisions with a Laya head.

    github.com/bladedevoff/stuntd

  15. sys1 logo

    A System One compatible API for open decision models, in Rust.

    github.com/alvarobartt/sys1

  16. snap logo

    Typed decisions from unstructured state, with no generated text.

    github.com/emnlmn/snap

  17. jev-harness logo

    An LLM proposes, Jev answers, code decides, every step leaves a receipt.

    github.com/TypeSafeAI/jev-harness

  18. JevAny logo

    JevAny (opens in a new tab)

    Benchmarks and evals

    Calibration-aware reinforcement learning for decision systems.

    github.com/weitianxin/JevAny

  19. gut logo

    gut (opens in a new tab)

    SDKs and integrations

    Elixir control-flow helpers for LLM and Jev judgment.

    github.com/vinibrsl/gut

  20. Kev logo

    An open-source System One engine with calibrated probabilities.

    github.com/arjun988/Kev

  21. Laya logo

    Open weights that answer typed questions in one forward pass, 33 ms on a T4.

    github.com/NandhaKishorM/laya

  22. rizzo-flow logo

    The open, local take on Jev: typed decisions without generating a token.

    github.com/Rizzo-AI-Academy/rizzo-flow

  23. JevHarness logo

    LLM-written Jev harnesses, with reward reflection over the full trajectory.

    github.com/TianyuCodings/JevHarness

  24. jeview logo

    jeview (opens in a new tab)

    SDKs and integrations

    A local visualiser: every Jev call your code makes, live.

    github.com/andududu/jeview

  25. evoke logo

    Software by reflex: a sentence picks a small program and runs it.

    github.com/evoke-build/evoke

  26. AnyJev logo

    Turn any LLM into a Jev-style decision model, with no training.

    github.com/nokia-applied-research/AnyJev

  27. discern logo

    discern (opens in a new tab)

    SDKs and integrations

    Uncertainty-aware pattern matching and control flow for Effect.

    github.com/doeixd/discern

  28. jev-rs logo

    jev-rs (opens in a new tab)

    SDKs and integrations

    A Rust, Jev-compatible /v1/systemone engine, one prefill per judgement.

    github.com/yijunyu/jev-rs

  29. hearim logo

    hearim (opens in a new tab)

    SDKs and integrations

    A Jev-compatible, multi-backend System One gateway in Go.

    github.com/ziozzang/hearim

  30. jevseo logo

    Typed SEO, AEO and GEO judgements, with the rules staying in code.

    github.com/epergaboni/jevseo

  31. jev-papers logo

    A thousand arXiv papers, one Jev decision each, checked by an LLM judge.

    github.com/stas4000/jev-papers

  32. ego-jev logo

    ego-jev (opens in a new tab)

    Agents and browsers

    One ~0.4 s typed decision per DOM step, instead of an LLM turn.

    github.com/ZephyrDeng/ego-jev

  33. dwim logo

    dwim (opens in a new tab)

    Agents and browsers

    Type what you want, and the right menu item runs in any Mac app.

    github.com/rohit9mehta/dwim

  34. jevgraph logo

    Knowledge graphs built from typed relation decisions, with the evidence kept.

    github.com/chenmingtang830/jevgraph

  35. Canny logo

    Canny (opens in a new tab)

    Coding and code review

    A warden that will not let a coding agent finish on a claim.

    github.com/qkal/Canny

  36. jevgrep logo

    jevgrep (opens in a new tab)

    Coding and code review

    Semantic code search for agents: find behaviour, not strings.

    github.com/nassim-arifette/jevgrep

  37. jevchat logo

    jevchat (opens in a new tab)

    Benchmarks and evals

    A chatbot built out of a model that only answers typed questions.

    github.com/kyle-pena-nlp/jevchat

  38. jevalyn logo

    jevalyn (opens in a new tab)

    SDKs and integrations

    A Rails-native decision layer: typed answers inside control flow.

    github.com/Ray-Hughes/jevalyn

  39. jcr logo

    jcr (opens in a new tab)

    Routing and model choice

    Turns a vague agent request into a deterministic command.

    github.com/NiazMorshed2007/jcr

  40. J++ logo

    J++ (opens in a new tab)

    Benchmarks and evals

    An experimental language for composing Jev questions.

    github.com/Towow-ai/jpp

  41. ChatJev logo

    ChatJev (opens in a new tab)

    Benchmarks and evals

    Driving the classifier as a next-token predictor, one token at a time.

    github.com/erik-dunteman/ChatJev

  42. jeval logo

    jeval (opens in a new tab)

    Benchmarks and evals

    Works out what a Jev confidence score is actually worth.

    github.com/rlaope/jeval

  43. JevPR logo

    JevPR (opens in a new tab)

    Coding and code review

    Risk review of a pull request, decided rather than written.

    github.com/HexyeDEV/JevPR

  44. jev-spec logo

    jev-spec (opens in a new tab)

    Coding and code review

    Checks generated code against the specification that asked for it.

    github.com/nozomi-koborinai/jev-spec

  45. UXRay logo

    UXRay (opens in a new tab)

    Security and abuse

    A screen overlay that flags manipulative interface patterns.

    github.com/zohaib-md/UXRay

  46. Bouncer logo

    A judgment layer that checks every Claude Code tool call against your policy.

    github.com/clownware/bouncer

  47. jevcumber logo

    jevcumber (opens in a new tab)

    Coding and code review

    Cucumber tests from the .feature file alone. No step definitions.

    github.com/RubyBrewsday/jevcumber

  48. winnow logo

    winnow (opens in a new tab)

    Context and memory

    A context sieve for Claude Code: Jev judges each tool result before it lands.

    github.com/GhalebDweikat/winnow

  49. pi-jev logo

    pi-jev (opens in a new tab)

    Context and memory

    A Pi extension: Jev picks the file excerpts, a local model writes the code.

    github.com/madeye/pi-jev

  50. mcp_jev logo

    mcp_jev (opens in a new tab)

    SDKs and integrations

    A local MCP server that runs ready-made Jev question packs.

    github.com/pedroknigge/mcp_jev

  51. jevkit logo

    jevkit (opens in a new tab)

    SDKs and integrations

    A Rust CLI for Jev, with a linter that checks questions before you pay.

    github.com/ariel-frischer/jevkit

  52. duckdb-jev logo

    duckdb-jev (opens in a new tab)

    SDKs and integrations

    Ask a question about every row in SQL, and get a real SQL type back.

    github.com/colliber/duckdb-jev

  53. reflex logo

    A small open decision model: state and typed questions in, probabilities out.

    github.com/kshetrajna12/reflex

  54. jev CLI logo

    jev CLI (opens in a new tab)

    SDKs and integrations

    A typed judgment CLI: questions in, answers and exit codes out.

    github.com/model-clis/jev

  55. daf-jev logo

    daf-jev (opens in a new tab)

    Benchmarks and evals

    A Python toolkit: question builders, confidence gates and calibration.

    github.com/docxology/daf-jev

  56. fastbrowse logo

    Jev picks each action; an LLM plans; every claim cites the page.

    github.com/agent-labs-dev/fastbrowse

  57. jev-ra logo

    jev-ra (opens in a new tab)

    Agents and browsers

    Browser use for coding agents, with Jev deciding each step in ~300 ms.

    github.com/brnyxx/jev-ra

  58. jev-reflex logo

    Claude thinks, Jev reacts: browser tasks at about 100 ms a decision.

    github.com/MSalvalaggio/jev-reflex

  59. jevwire logo

    jevwire (opens in a new tab)

    Agents and browsers

    A decision layer for agents: MCP server, library and Claude Code plugin.

    github.com/Brainwires/jevwire

  60. pi-heed logo

    pi-heed (opens in a new tab)

    Agents and browsers

    Checks every side-effecting tool call against what you asked for.

    github.com/Nyarlathoteppppp/pi-heed

  61. maza logo

    maza (opens in a new tab)

    SDKs and integrations

    A local MCP gateway with Jev tool discovery and a dashboard.

    github.com/prasanth263/maza

  62. capture logo

    A private Mac voice diary: local transcription, Jev sorting, Notion library.

    github.com/sgaabdu4/capture

  63. tenbin logo

    tenbin (opens in a new tab)

    Benchmarks and evals

    Split a judgment into Choice, Score and Noul, lint it, then measure it.

    github.com/simota/tenbin

  64. switchloom logo

    switchloom (opens in a new tab)

    Routing and model choice

    Deterministic model routing for coding agents, with a skill for Codex.

    github.com/instructa/switchloom

  65. jev-drone logo

    jev-drone (opens in a new tab)

    Robotics and devices

    A simulated drone that asks Jev for a judgment 2.5 times a second.

    github.com/RomanSlack/jev-drone