- Home
- AI Companion Apps
- Utsuwa
Utsuwa
What it is
Utsuwa is a free, open-source AI companion app built around a 3D VRM avatar, voice interaction, conversation memory, and a relationship system. It supports providers including OpenAI, Anthropic, Google, DeepSeek, xAI, OpenAI-compatible endpoints, Ollama, and LM Studio. You can load your own VRM model, browse or search memories, and add or delete them; local embeddings provide semantic recall. Voice choices include hosted and local services, with voice conversations, proactive messages, persistent memory, and image or video chat listed. Utsuwa runs on Android, Linux, macOS, Windows, web, and self-hosted setups, and can operate entirely on your machine with local models and voice services. The maker says there are no accounts, analytics, ads, or tracking cookies, and data stays on your device. In the hosted web app, requests may pass through Utsuwa servers; desktop messages go directly to the selected provider.
For and against
For
- Free open-source companion app
- Supports many model providers
- Allows custom VRM avatars
- Offers local operation and memory controls
- No accounts, ads, or tracking cookies
Against
- Desktop app is still in beta
- Desktop builds are not code-signed
- Hosted web requests may pass through Utsuwa servers
- Intended for adults aged 18 and over
The verdict
Utsuwa combines avatar customization, voice, memory, and broad model support in a free package. Its local operation and stated privacy choices will appeal to users who prefer device-based data handling.
Who it suits
Utsuwa suits adults 18 and over who want a customizable AI companion with avatars, voice, and persistent memory. It also fits users seeking local models or self-hosting options.
Plans and prices
Free
No subscription · No paywalled features · Bring your own model keys or use a local model
Read 5 Oct 2026 · utsuwa.ai
On the record
- Age
- The maker states that Utsuwa is intended for adults aged 18 and over.utsuwa.ai · read 5 Oct 2026
- Avatars
- Users can load their own VRM avatar models.utsuwa.ai · read 5 Oct 2026
- Desktop data routing
- In the desktop app, messages go directly from the device to the selected provider without passing through Utsuwa's servers.utsuwa.ai · read 5 Oct 2026
- Desktop status
- The desktop app is in beta, and its builds are not code-signed yet.docs.utsuwa.ai · read 5 Oct 2026
- Integrations
- The docs describe MCP tool connections including Home Assistant, Brave Search, and GitHub.docs.utsuwa.ai · read 5 Oct 2026
- Memory
- Local embeddings support semantic recall of conversations, and users can browse, search, add, and delete memories.docs.utsuwa.ai · read 5 Oct 2026
- Models
- It supports OpenAI, Anthropic, Google, DeepSeek, xAI, OpenAI-compatible endpoints, Ollama, and LM Studio.docs.utsuwa.ai · read 5 Oct 2026
- Offline use
- Utsuwa can run entirely on a user's machine with local models and local voice services.utsuwa.ai · read 5 Oct 2026
- Privacy
- The maker says there are no accounts, analytics, ads, or tracking cookies, and conversations, memories, and settings are stored on the user's device.utsuwa.ai · read 5 Oct 2026
- Product
- Utsuwa is an open-source AI companion app with a 3D VRM avatar, voice, memory, and a relationship system.docs.utsuwa.ai · read 5 Oct 2026
- Support
- The maker directs users to GitHub as the fastest way to reach the team.utsuwa.ai · read 5 Oct 2026
- Voice
- Voice options include ElevenLabs, OpenAI TTS, local TTS, OmniVoice, local Whisper, Groq, OpenAI, and browser speech recognition.docs.utsuwa.ai · read 5 Oct 2026
- Web data routing
- In the hosted web app, cloud provider requests may be relayed through Utsuwa's servers, which the maker says do not store messages or API keys or log conversation content.utsuwa.ai · read 5 Oct 2026
