Chitin vs Utsuwa
Chitin
chitin.netUtsuwa
utsuwa.aiSide by side
| Figure | Chitin | Utsuwa |
|---|---|---|
| Price from | $8.25/mo | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | — | Yes |
| Windows | — | Yes |
| macOS | Yes | Yes |
| Linux | — | Yes |
| iOS | Yes | — |
| Android | — | Yes |
| Self-hosted | — | Yes |
| Plans published | 3 | 1 |
| Spec score · AI Companion Apps | 8.2 (#10) | 7.5 (#29) |
| Integrations | The Agent Presentation Protocol connects agents that can send JSON to presentation surfaces, and the maker says any framework that speaks APP can drive Chitin surfaces. | The docs describe MCP tool connections including Home Assistant, Brave Search, and GitHub. |
| Privacy | The privacy policy says conversations are not stored beyond the active session and voice audio is not recorded or stored. | The maker says there are no accounts, analytics, ads, or tracking cookies, and conversations, memories, and settings are stored on the user's device. |
| Product | Chitin connects AI agents to animated avatars, voice companions, and other presentation surfaces. | Utsuwa is an open-source AI companion app with a 3D VRM avatar, voice, memory, and a relationship system. |
| Support | The support page says the team replies to email support requests within a day; Free includes community support and Plus includes priority support. | The maker directs users to GitHub as the fastest way to reach the team. |
| Voice | The Phone surface offers voice-first conversations, and Chitin Plus includes 13+ expressive voices. | Voice options include ElevenLabs, OpenAI TTS, local TTS, OmniVoice, local Whisper, Groq, OpenAI, and browser speech recognition. |
Plans
In their own words
Utsuwa
Utsuwa is a free, open-source AI companion app built around a 3D VRM avatar, voice, memory, and a relationship system. It supports models from OpenAI, Anthropic, Google, DeepSeek, and xAI, along with OpenAI-compatible endpoints, Ollama, and LM Studio. Users can load their own VRM avatars. Local embeddings support semantic recall, and users can browse, search, add, or delete stored memories. Voice options include hosted and local services. The listed capabilities include voice conversations, persistent memory, proactive messages, and image or video chat. Utsuwa can run entirely on a user's machine with local models and voice services. Its maker says there are no accounts, analytics, ads, or tracking cookies, and conversations, memories, and settings stay on the device. In the hosted web app, cloud-provider requests may be relayed through Utsuwa servers; the maker says those servers do not store messages or API keys or log conversation content. Desktop messages go directly to the selected provider, but the desktop app is in beta and its builds are not code-signed. The maker states that Utsuwa is intended for adults aged 18 and over.