Agents & workflows
Embedding Jev confidence decisions into real agent loops — games, code review, and software factories.
Projects in this category
- virattt/ai-hedge-fundGitHub ↗★ 64.4kPythonAn educational AI hedge-fund prototype with an optional Jev adapter for structured judgments in fund decision workflows.
- trycua/cuaGitHub ↗★ 31.5kRustCua’s preview jev-use example pairs Driver observation and execution with bounded Jev browser-action choices.
- browser-use/jev-ultrafastGitHub ↗★ 24.0kPythonA browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.
- vercel-labs/json-renderGitHub ↗★ 18.9kTypeScriptA Jev UI-composition experiment inside the json-render website that selects from predefined component and property options.
- jaredpalmer/kevGitHub ↗★ 9.8kPythonTiny Jev-like decision head built atop Qwen2.5-0.5B that can be trained and run locally on Apple Silicon MacBooks.
- lahfir/agent-desktopGitHub ↗★ 6.9kRustAn optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data.
- jarrodwatts/jev-traderGitHub ↗★ 3.1kTypeScriptA market-making experiment on Kuru’s MON-USDC book on Monad, with optional per-block Jev buy/sell decisions.
- TianyuCodings/NanoJevGitHub ↗★ 2.6kPythonNano replica of Jev featuring parallel decisions, dynamic candidate sets, and an end-to-end training and evaluation pipeline.
- awlevin/typesafe-computer-useGitHub ↗★ 1.3kPythonBuilds candidate actions from OCR and UI state for Jev to control macOS, calling a text model only when writing is needed.
- wy-coliney/jev-browser-useGitHub ↗★ 1.2kJavaScriptA Skill for Codex browser workflows: Jev chooses navigation, clicks, and scrolling while Codex handles text input and final checks.
- CelestoAI/celestoGitHub ↗★ 1.1k—A Celesto PR-review example prepares sandbox checks and compares a general model with Jev on candidate findings.
- thruwire/foremanGitHub ↗★ 803PythonSoftware Factory Foreman based on the TypeSafe Jev model.
- uezo/aiavatarkitGitHub ↗★ 703—An optional AIAvatarKit component uses Jev to judge turn endings from speech transcripts.
- devagrawal09/jev-reviewGitHub ↗★ 695TypeScriptA staged code-review workflow and local dashboard built with TypeSafe Jev.
- Sac-Y/Jev-cuGitHub ↗★ 631JavaScriptA Codex Computer Use loop sending text candidates to Jev while desktop tools observe and act.
- BennyKok/omg.devGitHub ↗★ 553TypeScriptAn omg.dev mobile testing script can use Jev to read the accessibility tree and choose the next interaction.
- kyotofin/tax-doc-classifierGitHub ↗★ 515TypeScriptA tax-document page classifier that uses Jev to choose from predefined IRS form and page categories.
- droidrun/mobile-jevGitHub ↗★ 459—Controls an Android phone through Mobilerun, with a web studio and CLI showing Jev decisions.
- fhshaik/typesafe-marioGitHub ↗★ 457PythonA TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.
- moritzkremb/jev-voice-browserGitHub ↗★ 422—Controls a Playwright browser by sending incremental speech transcripts to Jev.
- jkudish/jev-browserGitHub ↗★ 366—Drives a browser from a task and URL, returning the final page, screenshot and action trace.
- RomanSlack/jev-droneGitHub ↗★ 297PythonA MuJoCo drone experiment deriving scene features from camera buffers for Jev tactical advice.
- Knuckles92/OpenWhisperGitHub ↗★ 234PythonA dictation and meeting-notes app with optional Jev checks for topic changes, note-taker instructions and sensitive text.
- standardagents/jevpilotGitHub ↗★ 230JavaScriptA browser driving simulator where Jev chooses among locally generated paths and speeds.
- aowang-ai/jev-tradeGitHub ↗★ 225TypeScriptAn experimental Hyperliquid trading bot using Jev to choose long or short and whether to open, close, or hold.
- socai-io/jev-socialGitHub ↗★ 194JavaScriptJev-powered Instagram, TikTok, and LinkedIn research: typed routing, real browser evidence, streamed post cards, video capture, and cited socai reports.
- jexp/neo4jevGitHub ↗★ 181Jupyter NotebookNavigates a Neo4j graph one hop at a time, asking Jev which relationship to follow next.
- agent-labs-dev/fastbrowseGitHub ↗★ 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-agentGitHub ↗★ 131TypeScriptA Solana liquidity Agent with Jev shadow judgments compared against rule-based decisions.
- Ying-Kai-Liao/jev-browserGitHub ↗★ 128JavaScriptA browser library, CLI and MCP server where the caller supplies goals and text while Jev selects actions.
- trungdq88/youtube-sponsor-detectionGitHub ↗★ 116JavaScriptYouTube extension detecting sponsored segments from live audio and transcripts using Jev, skipping promotional blocks automatically.
- ChetasLua/jevmeterGitHub ↗★ 110PythonCreates edited videos with score meters by asking Jev to rate transcript sentences against selected rubrics.
- vinilana/jev-eval-agentGitHub ↗★ 109HTMLAgent tool evaluation harness comparing standard LLM tool selection against Jev routing across 100 mocked tools.
- ellipsis-dev/blinkGitHub ↗★ 101TypeScriptFinds files from a natural-language query using multiple walkers through the directory tree.
- AkashPriyadarshii/jev-seoGitHub ↗★ 97RustAn experimental Rust SEO/GEO CLI and MCP tool combining page checks, DuckDuckGo queries and optional Jev scoring.
- realZachi/typesafe-adblockGitHub ↗★ 94JavaScriptAn experimental Chrome extension that asks Jev whether candidate DOM elements are ads, then highlights or removes them.
- AboveColin/HA-JevGitHub ↗★ 82PythonTurns Jev judgments into Home Assistant sensors, such as checking whether finished laundry has been left unattended.
- yikangy873-gif/jev-desktopGitHub ↗★ 79JavaScriptTypeSafe Jev action selection inside Codex Computer Use
- OmniJev/PlayJevGitHub ↗★ 63JavaScript🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.
- zadescoxp/Jev-TradesGitHub ↗★ 57PythonA dashboard combining live crypto market data with Jev-guided paper trading; no broker or live-order API is connected.
- RafalWilinski/vibecheckGitHub ↗★ 50JavaScriptShows a Jev scorecard before posting on X, assessing draft clarity, tone, and possible offensiveness.
- unicodeveloper/jevocksGitHub ↗★ 48TypeScriptEveryday Stocks Status with Jev
- chy4pro/jev-for-chromeGitHub ↗★ 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-belayGitHub ↗★ 44JavaScriptClaude Code Stop hook that blocks an unverified done: reads the transcript for evidence, asks Jev once, fails open on everything else
- AkashPriyadarshii/jev-superpowersGitHub ↗★ 39JavaScriptSystematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions
- devanshbatham/commit-minerGitHub ↗★ 38RustClassifies Git commit messages and diffs with Jev for bug fixes, security fixes, CWEs, and change types.
- hqman/JevScoutGitHub ↗★ 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.
- AlbionaHoti/refgardenGitHub ↗★ 37TypeScriptA visual-reference gallery drawing from The Met, NASA and Cosmos, with Jev in local Explore mode.
- DanRWilloughby/snifftestGitHub ↗★ 36TypeScriptA Markdown and plain-text prose linter using local rules and optional Jev judgments.
- compozy/yoshiGitHub ↗★ 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/compozy
- phyous/tsai-scGitHub ↗★ 28PythonA Jev harness for StarCraft shareware’s Strongarm mission, pausing the game during state reads and inference.
- sorrycc/typesafe-snakeGitHub ↗★ 24TypeScriptSnake autoplayer driven by TypeSafe Jev, executing one discrete System One decision per tick with code-enforced legal moves.
- gaborishka/jev-canvasGitHub ↗★ 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_stockGitHub ↗★ 16PythonAn experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.
- forvela/jev-agent-browserGitHub ↗★ 15JavaScriptFast, bounded browser agents powered by Jev and agent-browser — typed actions, research, classification, and safe orchestration.
- 24601/AugustusGitHub ↗★ 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-askGitHub ↗★ 12TypeScriptTypeSafe Jev as the pi coding agent's quiet decision layer
- joelhooks/pi-fast-jev-compactionGitHub ↗★ 12TypeScriptPi extension: verbatim context compaction with TypeSafe Jev decisions
- leonaaardob/fast-dev-compactionGitHub ↗★ 12TypeScriptCodex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.
- valentynkit/jev-plays-pokemon-redGitHub ↗★ 9PythonPokemon Red on PyBoy: code owns the route and the arithmetic, Jev picks at branches in about 100 ms, calibration measured instead of assumed
- noplan-inc/limpetGitHub ↗★ 7PythonA Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev.
- milanboers/jev-plays-pokemonGitHub ↗★ 6PythonPlaying Pokemon Red using TypeSafe Jev
- shitianfang/wakegateGitHub ↗★ 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-jevGitHub ↗★ 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-demoGitHub ↗★ 1PythonThree.js drone simulator with a Python backend and live TypeSafe Jev navigation
Indexed in the Jev community ecosystem directory, data snapshot 2026-11-02.
Frequently asked questions
What is Agents & workflows?
"Agents & workflows" is a project category in the Jev ecosystem with 65 projects listed. Embedding Jev confidence decisions into real agent loops — games, code review, and software factories.
Which projects in "Agents & workflows" should I look at first?
Sorted by stars, start with: virattt/ai-hedge-fund, trycua/cua, browser-use/jev-ultrafast, vercel-labs/json-render, jaredpalmer/kev. Each has its own page covering positioning, language, license and alternatives in the same category.
Other categories
Keep going on this site
Try, docs, cases, and pricing link to each other. The next page is on this site.
- Site directoryThe full list of the pages above.
- EcosystemCommunity projects by category.
- Jev coverageEach entry names the decision and its evidence.
- Daily casesThe next batch of coverage cases, each day.
- CommunityPublic posts, each with its source.
- BuildsNotes on model and site updates.
- PrimitivesChoice, Noul, and Score together.
- PatternsRouting, fan-out, and composite scoring.
- SDKsHTTP, Python, and JavaScript.
Use clavue-jev
- Try a judgmentSend a state and read the answer.
- Live scenesTetris, six rapid judgments, and a sort. Copy the call and run it again.
- Judgment LabSupport triage, release review, compliance routing — edit and run on the spot.
- Compareclavue-jev and jev-1.13.0 answer the same question.
- DemosJudgment examples you can edit.
- PricingInput is $0.042 per million tokens. Output is free.
- APICall POST /v1/judge with a key.
Docs
- IntroductionWhat this model is for.
- Quick startThe smallest call that runs.
- System OneWritten here: a state plus one typed question. The model is clavue-jev.
- StateThe text you send in.
- ConfidenceHow sure the answer is, and when to act on it.
- ChoicePick one mutually exclusive option.
- NoulA yes/no question, returned as the probability of yes.
- ScoreRate along a scale.
- Intent routingOne Choice call dispatches the request.
- Confidence routingAct when confidence is high. Hand off when it is low.
- Fan-outAsk several questions of one state.
- Composite scoringFold several scores into one ranking.
- HTTP APIThe request shape without an SDK.
- Python SDKCall a judgment from Python.
- JavaScript SDKCall a judgment from JavaScript.
Cases
- Use-case mapWhich primitive people use for which job.
- GuardrailsA yes/no check before an action runs.
- Function callingPick which function to call.
- Classify with confidenceDo not act when the class is unsure.
- Semantic findFind the passages that match.
- Parallel questionsAsk the whole set in one call.
- Hierarchical classificationCoarse class first, then the fine one.
- Citation checkWhether a sentence is supported by the source.
- Entity alignmentWhether two names are the same thing.
- Skill suggestionChoose which skill fits the moment.