User repository on GitHub
A little 3D friend for your AI chats. It dresses for whatever you ask.
- Forks
- 5
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Tools & CLIs
Momo
A little 3D chat friend with 17 outfits that dresses for whatever you ask: keyword rules pick looks by default, and supplying a Jev key lets Jev choose the outfit, mood and reply length. The live demo runs without keys on local rules and written replies.
- Stars
- 21
- Language
- JavaScript
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Author
- mortspace
- Last verified
- Oct 2026
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- JavaScript
- Platforms
- Browser
- Capabilities
- Open sourceRuns locally
Highlights
- 17 outfits, each with its own prop, colour and face; by default keyword rules pick the outfit from what you ask.
- With a Jev key saved in ~/.momo/jev.env as JEV_AI_API_KEY and the --use-key-file flag, Momo asks Jev to choose the outfit, mood and reply length.
- Works with no keys out of the box using local rules and written replies; adding a free Gemini key gives real answers and the key stays on the server.
- Renders on any device: real 3D on a GPU, lighter meshes on software WebGL, and a Canvas 2D renderer when there is no WebGL at all.
- Plain JavaScript with no framework or build step; Node 20 or newer, npm install and npm run dev, live at feralui.dev/momo.
Quickstart
bash
git clone https://github.com/mortspace/momo
cd momo
npm install
npm run devWatch out
README reviewed 2026-10-17 and truncated inside the outfits table, so the full outfit list and card examples are not in the digest. Jev is a paid API billed per input token and is optional; the digest documents no quality comparison between keyword rules, Gemini replies and Jev-chosen looks.
Questions about this entry
Short answers drawn from the linked project or page.
A little 3D friend for AI chats that dresses for whatever you ask, with 17 outfits and a live demo at feralui.dev/momo. It answers without any keys by default using local rules and written replies.
If you paste a Jev key into Playground > Brain, or save JEV_AI_API_KEY in ~/.momo/jev.env and run with --use-key-file, Momo asks Jev to choose the outfit, mood and reply length instead of using keyword rules.
No. The README describes Jev as a paid API billed per input token. It is optional: by default Momo picks outfits with keyword rules and answers from local written replies with no keys at all.
With Node 20 or newer: git clone https://github.com/mortspace/momo, then cd momo, npm install and npm run dev, and open http://127.0.0.1:5281. Setting GEMINI_API_KEY adds real replies.
Momo answers from local rules and a set of written replies, and the live demo runs that way. A free Gemini key from Google AI Studio gives real answers, with the key kept on the server and never sent to the browser.
No. It renders real 3D on a GPU, falls back to lighter meshes on software WebGL, and uses a Canvas 2D renderer when WebGL is unavailable, so it is never swapped for a still image.
It is a chat companion rather than a decision tool. The digest truncates the outfits table, so the complete look catalog and the card examples are not covered, and Jev usage only happens when you supply your own paid key.
More Jev resources like this
A local Node app that asks whether an image is AI-generated: the browser measures 16 windows and a lens-fringe field and runs a bundled CLIP ViT-B/16 detector, then sends only a fixed fact dossier to JEV through OpenRouter for a verdict of likely_ai, likely_real or uncertain.
Jev Tools & CLIs#community#github#javascript
Community
GPTchatly/slop-scopeJavaScript
GPTchatly/slop-scopeJavaScriptA 32M-parameter typed-decision model plus a Chrome extension that runs entirely on-device with WebGPU/WASM and Moonshine speech recognition. Its local server speaks POST /v1/systemone, so existing Jev clients work by changing the base URL; a benchmark table claims zero option-order flips.
Jev Tools & CLIs#community#github#chrome-extension
Community
MeharPro/GenClassPython
MeharPro/GenClassPythonAn unofficial Chromium extension that adds a find-in-page bar: literal matches highlight instantly and locally, and with your own TypeSafe API key Jev also finds passages by meaning after you pause typing. Uncertain results never auto-scroll, and paid searches start only while you are in the bar.
Jev Tools & CLIs#community#github#chrome-extension
Community
Szewowsky/jev-findJavaScript
Szewowsky/jev-findJavaScriptA Chrome extension and web page that checks whether a public JavaScript or TypeScript repo's README matches its code: rules and five deterministic verifiers decide what is true, Jev labels README lines with calibrated confidence, and Haiku explains the findings.
Jev Tools & CLIs#community#github#javascript
A read-only triage dashboard that finds likely duplicate GitHub issues: lexical retrieval shortlists candidates, Jev answers four Choice questions per pair, and selected passages are shown side by side. It never closes issues.
Jev Tools & CLIs#community#catalog-import#logicrw
A minimal web UI for Jev, TypeSafe AI's first System One model: enter a free-text state, add typed questions, and Jev evaluates them all in parallel in one request, returning structured answers with calibrated probabilities instead of generated text.
Jev Tools & CLIs#community#github#javascript
Community
longspeed/jevJavaScript
longspeed/jevJavaScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.