A locally installed, power-user front end for chatting with many LLM APIs, image generators and TTS voice models.
kwaroran/Risuai
Cross-platform AI roleplay chat app that supports many LLM APIs, character cards, lorebooks, and long-term memory.
Open-source alternative to:SillyTavern
Character.AI
- Stars
- 1,780
- Forks
- 363
- Open issues
- 189
- Last commit
- yesterday
What is it?
Risuai, or Risu, is a cross-platform chat application and web app for roleplaying with large language models. Users create and run their own characters and stories, connecting to a range of model providers such as OpenAI, Claude, Gemini, OpenRouter, and Ooba.
The app covers the parts of roleplay that go beyond plain chat: lorebooks (world info) that inject background knowledge into prompts, regex scripts that transform model output, and memory systems including HypaMemory and SupaMemory for keeping long conversations coherent. Characters can switch portrait images based on expression, group chats let several characters share a scene, and text can be translated on input and output.
It is built with Svelte, TypeScript, Tauri, and Vite, and can be used from the official website, GitHub release builds, or a Docker container for web hosting.
Key features
- 01Supports multiple model APIs including OpenAI, Claude, Gemini, and OpenRouter.
- 02Lorebook (world info) for injecting background knowledge into prompts.
- 03Regex scripts for modifying model output.
- 04Group chats with multiple characters in one conversation.
- 05Expression-based character images and TTS voice output.
- 06Long-term memory via HypaMemory and SupaMemory.
Use cases
- Running long-form interactive fiction or roleplay with custom characters.
- Chatting with characters in a multi-character group scene.
- Hosting a shared roleplay chat service on a personal server via Docker.
Quick start
- 1
Get Risuai from the official website (recommended)
- 2
Or run the Docker container using the command in the README's Docker section
- 3
Open Risuai at localhost:6001 in your web browser after Docker starts
Things to know
- Licensed under GPL-3.0, a copyleft license that requires derivative works to be released under the same terms.
- The documentation wiki is marked as a work in progress.
In collections
Topics
FAQ
- What is Risuai?
- Cross-platform AI roleplay chat app that supports many LLM APIs, character cards, lorebooks, and long-term memory. Risuai, or Risu, is a cross-platform chat application and web app for roleplaying with large language models. Users create and run their own characters and stories, connecting to a range of model providers such as OpenAI, Claude, Gemini, OpenRouter, and Ooba.
- Is Risuai free to use? What license does it have?
- Risuai is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
- Is Risuai still maintained?
- Actively maintained. The last commit to Risuai was on Nov 6, 2026.
- What can I use Risuai for?
- Running long-form interactive fiction or roleplay with custom characters. Chatting with characters in a multi-character group scene. Hosting a shared roleplay chat service on a personal server via Docker.
- How do I install Risuai?
- Get Risuai from the official website (recommended) Or run the Docker container using the command in the README's Docker section Open Risuai at localhost:6001 in your web browser after Docker starts
- Where can I get Risuai?
- The source code and installation instructions are on GitHub: https://github.com/kwaroran/Risuai
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Single-file local runner for GGUF language models with a built-in KoboldAI web UI, supporting text, image, speech and music generation.
TypeScript SDK for writing one chat bot that runs across Slack, Teams, Google Chat, Discord, Telegram and more.
Self-hostable AI second brain that answers questions from the web and your own documents, with custom agents and scheduled automations.
A lightweight desktop AI chat client built with Tauri 2.0 and Next.js that works with cloud APIs and local models like Ollama, storing data locally.
A Svelte and FastAPI chat app that lets you ask questions about a GitHub repository or uploaded source folder, using online or local LLMs.