llt22/talkio

Local-first multi-AI group chat desktop app — pull gpt, Claude, Gemini, DeepSeek into one conversation. Tauri 2 + React 19.

What it solves

Talkio is a multi-model AI chat client that allows users to bring multiple different AI models into a single group chat. This solves the limitation of traditional one-on-one AI interactions by enabling models to discuss, debate, or collaborate on a single topic while maintaining distinct personas.

How it works

Built with Tauri 2 and React 19, the application acts as a local-first interface that connects directly to various AI providers (such as OpenAI, Anthropic, Gemini, and Ollama). It uses a unified streaming runtime to handle responses and a persona system to assign specific system prompts and parameters to each AI participant in a group chat. It also integrates the Model Context Protocol (MCP) to allow AI models to call external tools and access local files or Git repositories.

Who it’s for

It is designed for users who want to experiment with different AI perspectives, orchestrate complex discussions between multiple models, or use a privacy-focused, local-first AI desktop and mobile application.

Highlights

  • Multi-Model Group Chats: Bring multiple AIs into one conversation where they can see each other's messages and respond independently.
  • Persona System: Create custom roles (e.g., translator, code reviewer) with independent system prompts and temperature settings.
  • MCP Tool Integration: Connects to external tool servers via the Model Context Protocol for system capabilities like calendars and reminders.
  • Local-First Privacy: Stores all data in a local SQLite database and uses system credential stores for API keys.
  • Crosspatform Support: Works across Windows, macOS, Linux, and Android.
  • Advanced Rendering: Supports Markdown, Mermaid diagrams, KaTeX, and HTML/Three.js previews.
  • Workspace & Git Tools: Allows AI to read, search, and edit local project files and execute Git commands.

Related

  • Project
    senbo1/chat0

    An open-source, privacy-focused AI chat application that lets users bring their own API keys to interact with multiple AI models via a fast React interface.

  • Project
    Lucassssss/eechat

    A secure local AI chat application that supports the Model Context Protocol (MCP) for easy integration of AI tools and services while keeping data stored locally.

  • Project
    TypingMind/typingmind

    A professional chat UI frontend that lets users connect multiple AI models via API keys for a pay-as-you-go, private, and feature-rich chat experience.

  • Project
    u14app/neo-chat

    A self-hostable, local-first AI workspace that integrates multi-model chat, agentic workflows, and deep research tools with a focus on user data privacy.

  • Project
    Chevey339/kelivo

    Kelivo is an open‑source, Flutter‑based LLM client for Android, iOS, macOS, Windows and Linux. It lets you add any major LLM provider (OpenAI, Gemini, Claude, etc.) via API keys or account sign‑in, store chats and files locally, and optionally back them up to WebDAV/S3. A standout feature is *workspaces*: a sandboxed Linux environment (PRoot on Android, iSH on iOS) or native shell on desktop where the model can read/write files, run commands, and use tools like web search, image generation, speech‑to‑text, and custom “skills”. The app includes long‑term memory extraction, multilingual UI, theming, and extensive privacy controls, all under the AGPL‑3.0 license.