{"slug": "new-open-source-avatar-gives-your-ai-agents-a-face", "title": "New open-source AVATAR gives your AI agents a face", "summary": "ARPA Hellenic Logical Systems has released AVATAR, an open-source desktop companion that gives AI agents a visible VRM character with VRMA motion and lipsyncing. The Electron-based overlay runs locally on Windows, supports custom VRM/VRMA files, and includes a Motion Deck for keyboard-triggered gestures. Version 0.7.0 is available on GitHub under an MIT license.", "body_md": "Talking to a voice model today often feels like speaking into a well-lit void. The answers can be sharp, the TTS can sound human, and still something is missing: there is no presence on the desk. No glance when the model starts. No small gesture when a thought lands. Just a waveform, a chat log, or a black window that happens to speak.\n\nThat gap is why we built **AVATAR** — an open-source desktop companion from [ARPA Hellenic Logical Systems](https://arpacorp.net) that puts a **VRM** character on your screen, moves it with **VRMA** motion, and lipsyncs to live audio. It is not another chatbot. It is a thin, local-first presenter: your agents, tools, and listening habits stay yours; AVATAR gives them a body to occupy while you work.\n\nAVATAR runs primarily as an **Electron** transparent, always-on-top overlay on Windows. You drag a glass bar to move it, pin it over your IDE or browser, and let it follow sound from system output, a chosen app window, the mic, or a file. Bundled sample characters get you started; Settings → Directories points at your own `.vrm`\n\nand environment folders; optional **VRoid Hub** (bring-your-own OAuth) loads link-only characters for the session. Preferences live in a plain `config.yaml`\n\n. Contributors can also run the Vite app in the browser for UI and VRM work — the full companion experience is the desktop shell.\n\nUnder the hood it is deliberately boring in the best way: standard VRM / VRMA, Three.js, no mandatory cloud avatar SaaS. If your audio is local, the companion can stay local.\n\nPeople wiring **local LLMs**, voice pipelines, or agent stacks are an obvious audience — a face next to Ollama, a TTS demo, or a custom loopback makes the system feel finished instead of experimental.\n\nIt is also useful when the “agent” is not an agent at all:\n\nSame app; different reasons to keep it pinned.\n\n**v0.7.0** is less “new product” and more “the companion grows teeth for motion.” You can point Directories at a folder of your own `.vrma`\n\nclips. A validated **stage command layer** now owns play/set paths so triggers share one surface. **Motion Deck** (Settings → Motion) lets you shortlist gestures, bind keys, and fire a clip **once** without stealing the Animations selection you were looping — useful for streamers, demos, and anyone tired of opening Gear mid-conversation. Environment pickers got lighter (posters instead of hauling full GIFs into every thumb), and production builds keep trial `custom/`\n\nmedia out of the installer by default.\n\nNone of that replaces the core loop — overlay, audio, VRM — it makes the loop easier to drive from the keyboard and from whatever comes next (local buses, keyword maps, richer expression work).\n\n**Windows, no Node:** grab the installer from the [v0.7.0 release](https://github.com/ARPAHLS/avatar/releases/tag/v0.7.0) — [ AVATAR-Setup-0.7.0.exe](https://github.com/ARPAHLS/avatar/releases/download/v0.7.0/AVATAR-Setup-0.7.0.exe). Accept the EULA, launch, pick audio, leave it on top of whatever you already use.\n\n**From source (desktop):**\n\n```\ngit clone https://github.com/ARPAHLS/avatar.git\ncd avatar/avatar\nnpm install\nnpm run desktop\n```\n\n**Contributors / UI sandbox:** `npm run dev`\n\n→ [http://localhost:5173](http://localhost:5173) (browser; system loopback and overlay chrome stay Electron-only).\n\nDocs live in the repo ([Using the app](https://github.com/ARPAHLS/avatar/blob/main/docs/using-the-app.md), [installation](https://github.com/ARPAHLS/avatar/blob/main/docs/getting-started/installation.md)). Source, issues, and changelog: [ARPAHLS/avatar](https://github.com/ARPAHLS/avatar). MIT-licensed; cite via [ CITATION.cff](https://github.com/ARPAHLS/avatar/blob/main/CITATION.cff) if you use it in research.\n\nVoice models will keep getting better. The interesting question is whether they still sound like they are speaking from nowhere. AVATAR is our answer on the desk: open source, local-first, and finally a face for the things you already listen to.", "url": "https://wpnews.pro/news/new-open-source-avatar-gives-your-ai-agents-a-face", "canonical_source": "https://dev.to/arpa/new-open-source-avatar-gives-your-ai-agents-a-face-1h94", "published_at": "2026-08-16 08:51:01+00:00", "updated_at": "2026-08-16 09:11:52.961623+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "generative-ai"], "entities": ["ARPA Hellenic Logical Systems", "AVATAR", "VRM", "VRMA", "Electron", "Three.js", "VRoid Hub", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/new-open-source-avatar-gives-your-ai-agents-a-face", "markdown": "https://wpnews.pro/news/new-open-source-avatar-gives-your-ai-agents-a-face.md", "text": "https://wpnews.pro/news/new-open-source-avatar-gives-your-ai-agents-a-face.txt", "jsonld": "https://wpnews.pro/news/new-open-source-avatar-gives-your-ai-agents-a-face.jsonld"}}