PocketRisu/PocketRisu

Self-hosted AI roleplay chat platform you run on your PC or personal server, forked from Risuai

What it solves

PocketRisu provides a self-hosted platform for AI-driven roleplay chat, allowing users to maintain full control over their data and access their conversations across multiple devices via a web browser.

How it works

It operates as a server-side application that connects to various AI providers (such as OpenAI, Claude, Gemini, and Ollama) to generate responses. All user data, including character cards, chat histories, and settings, is stored in a centralized SQLite database on the server, ensuring that progress is saved and responses continue to generate even if the client device disconnects.

Who it’s for

Users who enjoy AI roleplay and want a private, self-hosted environment that supports multi-device synchronization and compatibility with the RisuAI ecosystem.

Highlights

  • Multi-device access: Access the chat interface from PC, tablets, or smartphones through a browser.
  • Server-side generation: Responses continue to be generated on the server even if the connection drops or the screen locks.
  • Broad AI provider support: Compatible with OpenAI, Claude, Gemini, DeepInfra, OpenRouter, and Ollama.
  • RisuAI Compatibility: Full support for RisuRealm character downloads, character cards, and lorebooks.
  • Advanced memory management: Includes lorebooks and HypaMemoryV3 for long-term context retention.
  • Cusomization: Supports regex scripts, plugins, and automatic translation for cross-language roleplay.

Related

  • Project
    pocketpaw/pocketpaw

    PocketPaw is a self-hosted, local-first AI agent platform that allows you to run and control your own intelligent assistants across multiple messaging apps and desktop interfaces without cloud subscriptions.

  • Project
    kwaroran/Risuai

    A cross-platform AI chatting application that provides advanced tools for roleplay, including multiple API support, long-term memory systems, and immersive visual assets.

  • Project
    a-ghorbani/pocketpal-ai

    PocketPal AI is a free, open‑source mobile app that runs quantized LLMs and neural TTS entirely on‑device (iOS & Android). It lets you chat, hear the assistant speak, and use built‑in tools (calculator, date‑time, HTML rendering) without any cloud connection. Models are downloaded once from Hugging Face and executed via llama.cpp (CPU/GPU/NPU). Users can create custom “Pals” or download community assistants from PalsHub. Developers can extend the app by adding new Talents, TTS engines, or locales; the codebase is a standard React‑Native project with native bridges to llama.cpp and ONNX Runtime. MIT‑licensed, privacy‑first, and fully offline.

  • Project
    open-webui/open-webui

    Open WebUI is a self-hosted AI platform that provides a user-friendly interface for interacting with AI models, supporting local models via Ollama and any OpenAI-compatible API. It offers features like plugins, role-based access control, persistent memory, RAG, and more, and can run entirely offline.

  • Project
    dappros/ethora

    Ethora is a multi‑platform SDK suite that adds real‑time chat, push notifications, file sharing, and LLM‑powered AI bots to web, mobile, and WordPress apps. It ships as a monorepo of sub‑modules (React, React‑Native, Android, iOS, WordPress) and can run on Ethora’s managed cloud or be self‑hosted via Docker/Helm. The platform includes a REST + XMPP backend, MCP server for AI‑agent integration, RAG demos, and optional blockchain wallet features. Getting started is as simple as cloning the repo, running `npx @ethora/setup` to obtain credentials, and installing the SDK for your target platform.