mindroom
A universal interface for AI agents with persistent memory, where every conversation has a home
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- 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).
License · maintenance · safety
Apache-2.0 (permissive) — 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.
last release 2026-08-14 (0 days) · last repo commit 2026-08-14 · 236 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 191,689 downloads/mo, #9,877 on PyPI
Alternatives
Verify before relying
# 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- 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.
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 on it.
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
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.
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).
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 runVerify 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
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.12 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 41 packagesagnoaiohttpaiosqliteanthropicanyioauthlibcerebras-cloud-sdkchromadbcron-descriptorcronitercryptographyfastapifiletypegoogle-authgoogle-genaigroqhttpxhumanizejinja2json5markdown-it-pymcpmdit-py-pluginsmem0aimindroom-nioopenaipackagingpydantic-settingspydanticpygments |
| Maintenance | Actively maintained 0 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 191,689 / month, #9,877 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14 |
Evidence: mindroom-2026.8.68-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “AI agents in chat rooms”
- mindroomMindRoom is a multi-agent runtime that deploys AI agents as…
- livekit-agentsA framework for building realtime multimodal and voice AI agents that…
- jupyter-ai-magicsJupyter AI Magics provides a JupyterLab extension that integrates AI…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also mem0ai · phidata · echo-agent · stashai · agent-framework-mem0 · autogen-agentchat · reme-ai · opencode-agent-hub · omnigent · honcho-ai