Radar check
What we found when we opened it. Every bar is one fact, with its date.
Last code pushed 22 Oct 2026, 5 days before this check.
Latest release v2026.10.220 on 22 Oct 2026.
Public since April 2023, a little over 3 years.
1,754 stars and 362 forks.
186 commits and 22 new issues in the last 90 days.
99 contributors. 53 pull requests merged in 90 days.
No security policy file says how to report a problem. No published security advisories.
How the bars are scored
- Alive. Days since the last code push: a week or less 100, a month 90, three months 70, six months 50, a year 30, eighteen months 15, older 0.
- Releases. Age of the latest GitHub release, on a similar scale; no bar when the project publishes no releases.
- Maturity. Age of the project: eight years 100, five 90, three 70, two 55, one 40, six months 25, younger 10.
- Adoption. Stars on a log scale: 100,000 stars is 100, 10,000 is 80, 1,000 is 60, 100 is 40.
- Activity. Commits in the last 90 days: 300 or more 100, 100 85, 30 65, 10 45, any 25.
- Community. People who have contributed: 100 or more 100, 30 80, 10 60, 5 40, 2 25, one 10.
- Security. A published security policy 80, none 40; published advisories are listed, not scored.
Checked by Repo Radar on 28 Oct 2026 from the repository on GitHub.
In simple English
Risuai is a program for chatting with artificial intelligence characters. You connect it to an artificial intelligence provider using your own key. It lets you create custom personalities, switch between different providers, and keep long conversations going. You can run it on your computer or host it on a server for yourself. The software is free to download, but you pay the artificial intelligence provider for the text it generates.
What it is
Risuai is an open-source chatting application built with TypeScript and Tauri (a way to build desktop apps using web technologies). It supports multiple language models, character expressions, lorebooks, and plugins.
What it is good for
It is good for solo builders who want a feature-rich interface for roleplaying or story generation with artificial intelligence models, without relying on hosted web services that restrict content.
Summary (Key Points)from the README
Key features
- Multiple API support: Works with OpenAI, Claude, Gemini, DeepInfra, Ooba, OpenRouter and more.
- Emotion images: Shows the image of the current character matching their expression.
- Group chats: Puts multiple characters into one chat.
- Plugins: Add your own features and providers and share them.
- Regex scripts: Modify model output with regular expressions, for example to build a custom GUI.
- Translators: Automatically translates input and output, so you can roleplay without knowing the model's language.
- Lorebook: Also known as world info or memory book, helping characters remember more.
- Themes: Choose from three themes: Classic, WaifuLike and WaifuCut.
- Prompting controls: Reorder prompts, impersonate inside prompts, and use conditions and variables.
- Text-to-speech: Converts the output text into voice.
- Additional assets: Embed images, audio and video in a bot and display them in chat or as backgrounds.
- Long-term memory: HypaMemoryV2/V3 memory compression and SupaMemory context management for long conversations.
Ways to install
| Platform or method | What it needs | Effort |
|---|---|---|
| Risuai website (recommended) | A web browser | Low |
| GitHub Releases | Downloading a release from the repository | Low |
| Docker | Docker with Compose, running a curl command, then opening localhost:6001 | Medium |
| Development build | Node.js 20.19+ or 22.12+ and pnpm | High |
Important
- Development prerequisites: Building from source needs Node.js 20.19+ or 22.12+ and pnpm.
- Wiki status: The documentation wiki is marked as a work in progress, so detailed information may be incomplete.
- Docker hosting: The Docker route is described as especially useful for web hosting, and it serves the app at localhost:6001 by default.
- Docker script source: The Docker command pipes a compose file fetched from the main branch straight into Docker, so review it first if you want to be careful.
Written by an AI model from the project’s README; not part of the review, and it can be wrong.
- Connects to many different language model providers like OpenAI, Claude, and Gemini.
- Includes advanced memory systems to keep characters remembering past events in long chats.
- Supports plugins and regex scripts to customize how messages look and behave.
- Requires your own API keys or a local server, meaning ongoing usage costs.
- Can be complex to configure due to the large number of prompting and memory settings.
- Building from source requires Node.js and pnpm installed on your machine.
SillyTavern
OpenRouter
- SillyTavern/SillyTavern35k stars
A popular node-based frontend for running roleplay chats with various large language models.
- vllm-project/vllm96k stars
A serving engine that makes one graphics card answer many requests at once.
- infiniflow/ragflow93k stars
A question-answering system built on a document collection, with the sources shown beside every answer.
- basicmachines-co/basic-memory4.3k stars
Gives an AI assistant a memory that is stored as plain text files you can read.
curl -L https://raw.githubusercontent.com/kwaroran/Risuai/refs/heads/main/docker-compose.yml | docker compose -f - up -d