mindroom

What it is and what it does

MindRoom is a self-hosted multi-agent orchestration platform that runs AI agents as native Matrix users. Each agent is a persistent identity with its own memory, credentials, and tool access, living in a Matrix homeserver and accessible through any Matrix client or via bridges to Slack, Telegram, Discord, WhatsApp, IRC, and email. You define agents in YAML or via a web dashboard, and they collaborate in threads, share context across platforms, and retain memory between sessions.

The runtime handles agent routing, persistent memory via Mem0 and ChromaDB, sandboxed execution of tools (shell, Python, web search, Gmail, GitHub, Google Docs, Home Assistant, and 100+ more), knowledge-base indexing (RAG), scheduled tasks, model routing per agent or room, voice transcription and synthesis, and hot-reload of configuration and plugins without downtime. It scales from a laptop to Kubernetes and supports enterprise features like isolated execution workers and egress approval.

Use it for:

• Run specialist AI agents that collaborate in threads and share context across Slack, Discord, and email.
• Build a persistent AI assistant with memory of preferences and access to email, calendar, and documents.
• Automate workflows with scheduled tasks, tool approvals, and human escalation in isolated containers.
• Deploy AI agents across organization boundaries via Matrix federation for secure collaboration.
• Index and search knowledge bases with RAG, giving agents context-aware retrieval.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

MindRoom is a multi-agent runtime that deploys AI agents as persistent Matrix users, giving them access to 100+ integrated tools and persistent memory across chat platforms including Slack, Telegram, Discord, and email via Matrix bridges.

Yes, if you want a self-hosted, multi-agent platform with persistent memory and cross-platform reach. MindRoom is actively maintained, has no known vulnerabilities, and offers multi-agent orchestration, sandboxed tool execution, and Matrix-native federation. The 41 dependencies and Python 3.12+ requirement are substantial, but justified for teams building AI agent systems. Start with hosted Matrix to evaluate before self-hosting.

Install

mindroom on PyPI

pip install mindroom

uv add mindroom

poetry add mindroom

Installing mindroom

Before you install

Low install friction with a pure-Python wheel. Active maintenance with a recent release (2026-08-14) and steady commit history. Requires Python 3.12+ and depends on 41 runtime packages including major frameworks (FastAPI, Pydantic, anthropic, openai) and specialized libraries (chromadb, mem0ai, mcp), which represent a substantial dependency footprint.

License in practice

Apache-2.0 is permissive and poses no restriction on commercial or private use. You can modify and redistribute the code freely under the same license terms.

Quickstart

# Install
pip install mindroom

# Initialize config and environment
uvx mindroom config init

# Add API credentials (e.g., ANTHROPIC_API_KEY)
# Then start the runtime
uvx mindroom run

Requires Python 3.12 or later. Requires a Matrix homeserver (can use hosted mindroom.chat or self-host). Requires API keys for at least one AI model provider (Anthropic, OpenAI, Google, Groq, or Cerebras).

Verify before relying

• Whether all 41 runtime dependencies are required for basic operation or if some are optional for specific features.
• Performance characteristics and resource requirements for typical multi-agent deployments.
• Stability and breaking-change history since first release in 2025-07-29.

Package facts

Evidence: mindroom-2026.8.68-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading