mindroom-ai/mindroom

AI agents that know you and your work, in a chat app anyone can use. Open source, any model, self-host or hosted.

What it solves

MindRoom provides a unified, self-hostable framework for AI agents that integrate with your personal and professional tools. It solves the fragmentation of AI assistants by allowing you to connect your accounts (email, calendar, documents) once and use them across any LLM (local or cloud) and any chat platform (Matrix, Slack, Telegram, WhatsApp, Discord).

How it works

MindRoom treats every agent as a real user on the Matrix open chat standard. This architecture allows agents to be deployed as a fleet of specialists or teams that can collaborate in shared threads. Users can route different agents to different models (e.g., local Ollama for private data, frontier models for coding) and manage them via a web dashboard or YAML configuration. The system includes a persistent memory layer (Mem0 + ChromaDB) and a RAG system for indexing local folders or Git repositories.

Who it’s for

  • Individuals looking for a private, self-hosted personal assistant for scheduling, note-taking, and smart home control.
  • Teams needing shared AI agents that can search across company email, tickets, and code to generate reports or triage inboxes.
  • Developers who want to build and deploy multi-agent systems with sandboxed code execution and deep tool integrations.

Highlights

  • Multi-Platform Access: Connects to Matrix and bridges to Slack, Telegram, WhatsApp, and Discord.
  • Extensive Tooling: 100+ integrations including Gmail, GitHub, Jira, and support for MCP servers.
  • Human-in-the-Loop: One-tap approval cards for agent actions and a persistent Chromium browser that users can take over live.
  • Privacy-First: Support for local models, local memory, and end-to-end encryption via Matrix.
  • Advanced Agentics: Automatic skill learning, multi-agent orchestration, and adaptive participation in group threads.

Related

  • Project
    Agenta-AI/agenta

    Agenta is an open‑source, self‑hostable workspace for building AI agents that can be chatted with, shared with a team, and run in the background. It supports many LLM providers, integrates with thousands of SaaS tools, offers permission controls, tracing, and scheduling, and provides a web UI plus a rich developer ecosystem.

  • Project
    androoAGI/starnet

    StarNet is a local‑first desktop app that lets you build and run multiple AI agents in a pixel‑art space‑station UI. Each room represents a bounded team with its own memory, permissions and budget. Agents use real LLM providers (OpenAI, Anthropic, Google, OpenRouter, or a local Ollama model) and can call tools, send messages to chat platforms, run scheduled recipes, and output real files. The visual layout is the live workflow, and all state (transcripts, spend logs, memory) is persisted on disk with secrets kept in the OS keychain.

  • Project
    microsoft/agent-framework

    Microsoft Agent Framework is an open‑source SDK for building production‑ready AI agents and multi‑agent workflows in Python, .NET, and Go. It provides provider‑agnostic LLM access, graph‑based orchestration, middleware, observability, and easy Azure/Foundry hosting.

  • Project
    joinly-ai/joinly

    A connector middleware that enables AI agents to join and participate in video calls on platforms like Zoom, Google Meet, and Microsoft Teams via voice and chat.

  • Project
    zhayujie/CowAgent

    CowAgent is an open‑source, self‑hosted AI assistant that plans tasks, runs tools, keeps a personal knowledge base, and can operate as a team of cooperating agents. It supports many LLM providers, multimodal input, dozens of chat channels (Telegram, Slack, WeChat, etc.), a plug‑in skill system, and a three‑tier memory with nightly “Deep Dream” distillation. Install via a one‑line script or Docker, manage everything through a web console, and extend the system through the public Skill Hub or custom tool integrations.