GitHub - Amal-David/awesome-jev · GitHub

Skip to content

Navigation MenuSign inAppearance settingsPlatformAI CODE CREATIONGitHub CopilotWrite better code with AIGitHub Copilot appDirect agents from issue to mergeMCP RegistryIntegrate external toolsDEVELOPER WORKFLOWSActionsAutomate any workflowCodespacesInstant dev environmentsIssuesPlan and track workCode ReviewManage code changesCode QualityEnforce quality at mergeAPPLICATION SECURITYGitHub Advanced SecurityFind and fix vulnerabilitiesCode securitySecure your code as you buildSecret protectionStop leaks before they startEXPLOREWhy GitHubDocumentationBlogChangelogMarketplaceView all featuresSolutionsBY COMPANY SIZEEnterprisesSmall and medium teamsStartupsNonprofitsBY USE CASEApp ModernizationDevSecOpsDevOpsCI/CDView all use casesBY INDUSTRYHealthcareFinancial servicesManufacturingGovernmentView all industriesView all solutionsResourcesEXPLORE BY TOPICAISoftware DevelopmentDevOpsSecurityView all topicsEXPLORE BY TYPECustomer storiesEvents & webinarsEbooks & reportsBusiness insightsGitHub SkillsSUPPORT & SERVICESDocumentationCustomer supportCommunity forumTrust centerPartnersView all resourcesOpen SourceCOMMUNITYGitHub SponsorsFund open source developersPROGRAMSSecurity LabMaintainer CommunityGitHub StarsArchive ProgramREPOSITORIESTopicsTrendingCollectionsEnterpriseENTERPRISE SOLUTIONSEnterprise platformAI-powered developer platformAVAILABLE ADD-ONSGitHub Advanced SecurityEnterprise-grade security featuresCopilot for BusinessEnterprise-grade AI featuresPremium SupportEnterprise-grade 24/7 supportPricingSearch/Sign inSign upAppearance settings

You signed in with another tab or window. Reload to refresh your session.
You signed out in another tab or window. Reload to refresh your session.
You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

Amal-David

/

awesome-jev

Public

Notifications
You must be signed in to change notification settings

Fork
1

Star
13

Code

Issues
0

Pull requests
1

Actions

Projects

Security and quality
0

Insights

Additional navigation options

Code

Issues

Pull requests

Actions

Projects

Security and quality

Insights

mainBranchesTagsGo to fileCodeOpen more actions menuLatest commit History37 Commits37 CommitsFolders and filesNameNameLast commit messageLast commit date.github.github  datadata  docsdocs  examplesexamples  scriptsscripts  skills/jev-curatorskills/jev-curator  templatestemplates  teststests  .gitignore.gitignore  AGENTS.mdAGENTS.md  CONTRIBUTING.mdCONTRIBUTING.md  LICENSELICENSE  README.mdREADME.md  SECURITY.mdSECURITY.md  SOURCES.mdSOURCES.md  View all filesRepository files navigationREADMEContributingLicenseSecurityMore itemsAwesome Jev
From an interesting demo to code you can actually understand.
A curated starting point for TypeSafe Jev: reviewed projects, reusable skills, small code examples, and creator demos from X, GitHub, and YouTube.
33 reviewed picks — start with the source-reviewed selection, not the raw index.
Browse reviewed picks · Freshness and link health
Evidence legend: Reviewed = primary source inspected · Indexed = community listing · Auto-discovered = README keyword match. These labels are not security certifications.
Last discovery: 2026-09-22T13:30:23Z (UTC). Latest repository metadata date: 2026-09-22. Unavailable repositories at last check: 13. Coverage, failures and run receipts.
Navigate: Quick start · Choose a path · CUA & drivers · Reviewed picks · OpenRouter winners · Watch demos · Search the catalog · Contribute

Source-reviewed does not mean security-audited. Keep credentials private and inspect permissions before running a project.

What is Jev?
Jev is TypeSafe AI's model for answering typed questions about text or JSON: choose an option, estimate whether something is true, or score it against a rubric. Use it for bounded decisions such as routing, ranking, or selecting an agent's next action; use a generative LLM when you need new prose, code, or an open-ended plan. Your application still controls permissions, validation, and execution. Official documentation · Official Python quick-start source.
20-second quick-start
JSON in → one typed decision out. With typesafe-sdk installed and TYPESAFE_API_KEY set, this makes one billable API request:
from typesafe_sdk import Choice, TypeSafeClient

with TypeSafeClient() as client:
result = client.system_one(
state={"document": "I was charged twice."},
questions={"team": Choice(
instructions="Which team should handle this ticket?",
criteria={"billing": None, "technical": None, "other": None},
)},
)
print(result.choices["team"].choice) # e.g. billing; actual output can differ
No key yet? Clone this repository and run python3 examples/route_ticket.py to inspect an offline request without making an API call. Setup and next steps · More question packs.

Browser Use / @gregpr07. Author recording, not our benchmark. Implementation · More demos and videos.
Choose your path
Build your first typed classifier → JSON input, a Choice question, and your first response.
Use Jev in an agent → Select observed actions, validate them, and keep a fallback.
Explore a local alternative → Independent implementations, hardware requirements, and important differences.
Computer use and drivers
Computer-use map: integrations, drivers, skills, and local alternatives.
Native/desktop: Cua Driver + jev-use, Jev Cua, and jev-bot. Browser: compare Jev Ultrafast, the smaller browser skill, Jev Browser, and the existing-connection Codex skill in the map.
Keep the layers separate: Jev selects; the driver executes; application code verifies. Browser Harness and Cua Driver are supporting runtimes, not Jev models. CUA-S1-FORMS and Jevlike are independent local-model projects, not official Jev weights. A locally installed agent may still call hosted Jev.
Reviewed picks
These are the editorial selections. Follow a project immediately, or open the full reviewed page for its concrete Jev role, source evidence, review date, and reuse notes.
Start building: TypeSafe JavaScript SDK · TypeSafe Python SDK · Jev Logs · Jevify · Official TypeSafe skill · Skillbox.
Use it in an agent or app: Cua Driver + jev-use · Jev Browser (MCP, CLI, library) · Jev Browser Skill · Jev Browser Use (existing Codex connection) · Jev Cua (Codex/Waku) · Jev Ultrafast · Jev voice browser · jev-bot (@compootor) · TypeSafe computer use (macOS) · Foreman · Jev MCP · jev_search · TypeSafe MCP · tisco · Vibe Domain · Browser Harness (supporting driver) · Home Assistant Jev.
Explore games and creative tools: Jev Chess · Jev Plays Snake · JevAI for XMage · JevPilot · PROMPT FPS / Jev Doom · TypeSafe Mario · Jev Music Playground.
Investigate local alternatives: CUA-S1-FORMS (independent specialist) · Jevlike (independent option scorer) · OpenJev SGLang.
All 33 reviewed picks — with evidence, dates and reuse notes
OpenRouter community winners
OpenRouter's 21 September 2026 showcase named five projects: JevAI for XMage, Jev Chess, tisco, Vibe Domain, and jev_search.
Explore game decisions, transcript search, domain ranking, and two-pass code search. Each winner has its original post and publisher screenshot in the visual gallery, plus source and implementation notes. Three have linked source repositories; the other two are public project pages, not verified open-source releases. “Winner” is OpenRouter's designation, not our ranking or a security certification.
Find a project
On GitHub: open the categorized catalog, choose a heading from its outline, and use Cmd/Ctrl+F for a project, creator, or keyword.
Prefer filters? The local catalog viewer starts with reviewed picks. Search by keyword, then filter by evidence level, category, available code/skill/demo, and license. It runs without dependencies, sign-in, API keys, or a server; the viewer's data is embedded at build time. Browse instructions · Machine-readable catalog.
Why this exists
A compelling clip often leaves the useful questions unanswered: what did Jev decide, where is the implementation, and what can I reuse? This directory connects the original demo to the code and separates inspected sources from the much larger discovery queue. A high raw entry count is not the goal; a shorter path to something useful is.
What belongs here?
A concrete Jev integration, demo, skill, SDK, reusable snippet, tutorial, or clearly labeled independent reproduction—with a traceable primary source and a specific explanation of Jev's role. Generic type-safety libraries, unrelated projects named Jev, unsupported performance claims, and duplicate listings do not belong.
Repositories are deduplicated by canonical owner/name; renamed projects should point to their successor. Maintainers can correct an entry, remove it from the reviewed selection, or exclude it from future imports. Inclusion, deduplication, and removal policy.
Contribute
Suggest a demo or correction with the original creator, a source link, what Jev decides, and any code, skill, or recording. For a PR, edit the relevant JSON source and run python3 scripts/build.py, then python3 -m unittest discover -s tests -v and python3 scripts/build.py --check. Contributor guide.
The four-hour workflow performs bounded discovery and rotating checks; it does not continuously inspect every website. Freshness, unavailable repositories, media errors, and run receipts distinguish actual checks from scheduled intentions.

Safety, licensing, and evidence limits
Source review is not a security audit, successful execution test, benchmark replication, or endorsement. Inspect permissions and outbound data before installing hooks, browser extensions, or agent skills. Keep API credentials private; demos can use paid inference, privileged desktop access, or logged-in browser profiles.
Recordings, illustrations, fixtures, and mock modes are labeled where known. A live-looking dashboard is not evidence of real inference or profitable trading. Independent reproductions are not official Jev weights or proof of equivalent quality.
Missing licenses remain not-checked, not-detected, or NOASSERTION, not assumed permission to reuse. Original code and writing follow the repository's license; imported metadata and linked media retain their original terms. This is an unofficial community directory, not endorsed by TypeSafe AI. Security policy · Attribution.

Watch Jev in action
Original creator media, linked to the implementation. Click a preview to watch the source. Animated GIFs play inline; original GitHub video attachments appear as players below. X and YouTube open on their own platforms.
From X: demos and the original roundup

Browser Use × Jev Ultrafast
Watch a browser choose operations and DOM targets; a separate model writes text.
▶ Watch on X · Code · Source
Browser Use · @gregpr07 — Animated author recording. This narrow flight-search demonstration is not a general reliability benchmark.

Talk to a browser
Partial speech becomes typed intents and observed page targets; Playwright acts.
▶ Watch on X · Code · Source
Moritz Kremb · @moritzkremb — Creator post preview when accessible. Keep its browser-control server private; a recording is not a security audit.

Jev on the Mac desktop
OCR and accessibility observations become choices for desktop actions.
▶ Watch on X · Code · Source
@awlevin — Creator post preview when accessible. Screen content may be private; real use needs screen-recording and accessibility permissions.

An independent agent supervisor
Jev assesses worker progress and verification needs; code decides interventions.
▶ Watch on X · Code · Source
Josh Rosen · @JoshARosen — Architectural experiment. Not a replacement for tests, review, or permission checks.
No reliable preview image was returned. The original watch link is retained.

An order-book decision loop
Typed buy/sell judgments inside a bounded quoting and execution loop.
▶ Watch on X · Code · Source
Jarrod Watts · @jarrodwatts — The documented default is mock/dry-run. A dashboard does not prove live inference, profitability, or safe custody.

The community roundup
The discovery thread that seeded this collection; follow the original creators.
▶ Watch on X · Source
Moritz Kremb · @moritzkremb — Roundup image, not a separate working project. This directory does not claim to capture every reply.

OpenRouter winner: JevAI for XMage
Legal game actions become Jev choices; the hybrid combines XMage search with model judgment.
▶ Watch on X · Code · Source
ShiftSad · screenshot published by OpenRouter — Publisher screenshot, not a recording or our test. The reported 11-6-3 result belongs to the hybrid; pruning is off by default. Award announced 2026-09-21.

OpenRouter winner: Jev Chess
A shared chess game displays Jev probabilities over legal move candidates.
▶ Watch on X · Source
sliday · screenshot published by OpenRouter — Publisher screenshot; Source opens the project page. No public repository or code license verified. We did not play a move or reproduce the results. Award announced 2026-09-21.

OpenRouter winner: tisco
Search spoken content, review transcript matches, and approve clip organization in a terminal.
▶ Watch on X · Code · Source
cairodavila · screenshot published by OpenRouter — Publisher screenshot. Jev judges transcripts, not video pixels. Audio uploads, live model calls, and file changes have separate data and approval implications. Award announced 2026-09-21.

OpenRouter winner: Vibe Domain
Separate candidate availability checks from ranking names against a requested vibe.
▶ Watch on X · Source
OB Studio / Oliver · screenshot published by OpenRouter — Publisher screenshot; Source opens the project. The page documents a no-key heuristic mode distinct from live Jev. No public repo verified; recheck availability at a registrar. Award announced 2026-09-21.

OpenRouter winner: jev_search
Keyword-density code prioritizes files; Jev evaluates passages in two passes.
▶ Watch on X · Code · Source
caio0452 · screenshot published by OpenRouter — Publisher screenshot. The author labels the project AI-generated and not for production. Selected source text reaches OpenRouter; no project code was executed here. Award announced 2026-09-21.

Screenshots, animated demos, and implementation diagrams

Jev Tetris: see the decision
Code enumerates reachable placements; Jev chooses and the board visualizes its preferences.
Open demo / recording · Code · Source
thelau — Author UI still. A mock mode also exists; the screenshot alone does not establish live inference.

A structured code-review dashboard
Follow staged risk checks, evidence selection, and severity judgments in a local UI.
Open demo / recording · Code · Source
devagrawal09 — Author dashboard screenshot. Findings are review prompts, not proof of a defect or a security certification.

Needle: find by meaning
Score source passages and select the relevant sentence without generating a new answer.
Open demo / recording · Code · Source
Shubhamsaboo / awesome-llm-apps — Author screenshot of the semantic-find interface. Live requests use Vercel AI Gateway and send selected text.

How Jevthoven composes
A prompt becomes a musical plan, bounded choices, editable notes, and MIDI.
Open demo / recording · Code · Source
cocktailpeanut — Author architecture illustration, not a screenshot or an audio-model result. The full recording appears below.

Three primitives, made visible
Explore Noul, Choice, and Score through an interactive decision playground.
Open demo / recording · Code · Source
davila7 — Explanatory illustration, not an actual response or timing result. Hosted live examples require a key.

A meaning-based Mac launcher
Local search proposes files and history items; Jev ranks the intended targets.
Open demo / recording · Code · Source
dabit3 — Historical author screenshot from the archived experiment. Its README points to a successor; this is not the current UI.

Semantic shell suggestions
Jev ranks a bounded set of previous commands; the user accepts a suggestion.
Open demo / recording · Code · Source
mrnugget — Animated author demo uses fabricated history. Do not send sensitive real shell history without reviewing data handling.

A browser skill you can read
A recorded Hacker News walkthrough shows observed controls, typed choices, and execution.
Open demo / recording · Code · Source
zurfyx — Animated author recording, plus an MP4. A deliberately bounded reference implementation, not a complete browser agent.

Full recordings — play inline
These are the creators' original GitHub-hosted uploads, not re-encoded copies. A direct watch link is retained for clients that do not render a player.
Abide — checking project rules during an agent session — the recording could not be verified by the latest public-access check. View the creator source.
Jevthoven — from a prompt to editable music
Watch typed musical decisions turn into an editable multitrack composition.

jevthoven-cropped.mp4

Open recording · Repository · Creator source
cocktailpeanut — Code renders notes and audio. Fixture/manual modes are distinct from billable live Jev decisions.
jev-align — improve a decision with human labels
Find uncertain examples, label them, and review proposed AI-function improvements.

jev-align-3.mp4

Open recording · Repository · Creator source
Sutro — Experimental active-learning CLI. Training improvement is not held-out quality; inference and reflection models may both bill.
Longer walkthroughs on YouTube

A full Jev walkthrough
A longer introduction and practical demonstrations from Moritz.
▶ Watch on YouTube · Source
Moritz | AI Systems — Linked video, not an independently reproduced tutorial. Title and creator metadata are checked through YouTube oEmbed when accessible.

An email-classification walkthrough
A creator walkthrough of applying Jev to email classification.
▶ Watch on YouTube · Source
vogel — Linked video, not an independently reproduced tutorial. Title and creator metadata are checked through YouTube oEmbed when accessible.

Practical ways to use Jev
An overview of possible applications and implementation ideas.
▶ Watch on YouTube · Source
Mark Kashef — Linked video, not an independently reproduced tutorial. Title and creator metadata are checked through YouTube oEmbed when accessible.

Source notes: media remain hosted by their creators/platforms; this repository does not relicense them. Public X mirror metadata is used only to locate a poster, not to certify a demo. Reachable media is not proof of live inference, security, or benchmark performance. No project was executed for this gallery.
Media sources and link-check receipts · Suggest a visual demo

Curated X demos: compact source index
Curated X demos
Sources include Moritz Kremb's roundup and OpenRouter's five community winners. The five OpenRouter winner posts are covered; Moritz's thread is not claimed complete. Full X index and access notes.

Demo
What Jev does
Watch / inspect

Voice-controlled browser — @moritzkremb
Maps partial speech transcripts to typed intents and observed page targets; Playwright executes the selected action.
X demo · repo · source

Browser Use × Jev Ultrafast — @gregpr07
Chooses an operation and compatible DOM target in one decision cycle; a separate model supplies typing text.
X demo · repo · source

macOS computer use — @awlevin
Selects desktop actions from OCR and accessibility-derived state, with a separate writer for free text.
X demo · repo · source

Foreman coding-agent supervisor — @JoshARosen
Assesses coding-worker progress and verification needs while deterministic policy decides interventions.
X demo · repo · source

Jev trading-loop demonstration — @jarrodwatts
Uses typed buy/sell judgments in an order-book loop, while code owns quoting, limits, and execution.
X demo · repo · source

JevAI for XMage — ShiftSad · featured by @OpenRouter
XMage supplies legal plays; pure and hybrid players use Jev for bounded decisions and selection among searched lines.
X demo · repo · source

Jev Chess — sliday · featured by @OpenRouter
A shared internet-versus-Jev chess game visualizes probabilities over legal move candidates.
X demo · project · source

tisco — cairodavila · featured by @OpenRouter
Jev searches transcript meaning; code previews and applies approved clip moves and renames.
X demo · repo · source

Vibe Domain — OB Studio / Oliver · featured by @OpenRouter
Ranks domain candidates against vibe and keyword preferences, separately from registry and availability checks.
X demo · project · source

jev_search — caio0452 · featured by @OpenRouter
Keyword-density code prioritizes files and chunks; Jev judges passages in a fast first pass and a broader second pass.
X demo · repo · source

Star to bookmark the reviewed collection. A corrected source link or a well-explained contribution is just as valuable.
AboutNo description, website, or topics provided.ResourcesReadmeLicenseContributingContributingSecurity policySecurity policyActivityStars13 starsWatchers0 watchingForks1 forkReport repositoryReleasesPackagesContributorsLanguages

Footer

© 2026 GitHub, Inc.

Footer navigation

Terms

Privacy

Security

Status

Community

Docs

Contact

Manage cookies

Do not share my personal information

You can’t perform that action at this time.

The awesome-jev repository serves as a curated starting point for TypeSafe AI’s Jev model, which is designed for answering typed questions about textual or JSON data by allowing users to choose an option, estimate a truth value, or score criteria against a rubric. This capability is intended for making bounded decisions, such as routing, ranking, or selecting the next action for an agent, distinguishing it from general generative Large Language Models which are better suited for producing new prose, code, or open-ended plans. The system operates on a principle where the application layer retains control over permissions, validation, and execution, ensuring that Jev acts as a decision-making filter rather than an autonomous executor.

The core mechanism for utilizing Jev involves a process where structured input, such as JSON, is processed to yield a single typed decision. This is demonstrated through a quick-start example using the typesafe_sdk, where a request specifying a state and a multi-criteria question results in a specific choice determination. The architecture emphasizes a clear separation of responsibilities: Jev handles selection, while supporting components, such as drivers, execute the actions, and the main application code performs verification. This modular approach allows for the integration of various modalities, including computer use, browser interactions, and specific skills, by keeping the Jev model distinct from the execution runtime.

The repository contains a collection of resources, including reviewed projects, reusable skills, small code examples, and creator demonstrations drawn from sources like X, GitHub, and YouTube. This collection highlights diverse applications ranging from building initial typed classifiers to integrating Jev into sophisticated agent workflows and exploring local alternatives. Specific paths outlined include building classifiers, deploying Jev within an agent framework for action selection and fallback mechanisms, investigating local implementations, and integrating Jev with computer use and drivers.

The reviewed picks feature various practical implementations, such as integrating Jev with browser skills, demonstrating voice-controlled browser capabilities, and developing agent supervision systems where Jev assesses progress and guides interventions. Furthermore, the repository showcases successful community-endorsed projects, including those recognized by OpenRouter for applications like JevAI for XMage, Jev Chess, tisco, Vibe Domain, and jev_search, indicating the model's utility in specialized domains such as legal game actions, transcript searching, domain ranking, and code-based file prioritization.

The collection also provides artifacts demonstrating the conceptual and operational possibilities of Jev, such as exploring interactive decision playgrounds for primitives like Choice and Score, visualizing complex decisions like in the Jev Tetris example, and illustrating complex compositions in the jevthoven framework. The documentation stresses that source review does not equate to security auditing, and users must exercise caution regarding credentials and inspection of permissions before running any project. The repository functions as a dynamic, traceable catalog linking demonstrations and source evidence to facilitate reproducible experimentation and community contribution regarding the model’s practical deployment.