mirobody
installs/mo · pypistarsforks
How to install mirobody?
thetahealth/mirobody
$git clone https://github.com/thetahealth/mirobodyYour Data, Your AI — Health, Finance & More. Open Source, Privacy-First.
README.md
| 1 | <div align="center"> |
| 2 | |
| 3 | # 🚀 Mirobody |
| 4 | |
| 5 | **Your Data, Your AI — Health, Finance & More. Open Source, Privacy-First.** |
| 6 | |
| 7 | [](https://mirobody.ai) |
| 8 | [](https://www.thetahealth.ai/) |
| 9 | [](https://pepy.tech/projects/mirobody) |
| 10 | |
| 11 | *Self-hosted data platform that bridges your personal data with the latest AI capabilities* |
| 12 | |
| 13 | **AI Engine:** |
| 14 | |
| 15 | - 🌐 **HTTP Remote MCP Server** - Deploy and access MCP tools over HTTPS |
| 16 | - 🎯 **Claude Agent Skills Support** - Develop tools using standard Skills format (SKILL.md) |
| 17 | - 🔄 **Universal Tool Adapter** - Works with ChatGPT, Claude, Cursor, and more |
| 18 | - 🔌 **Pluggable Data Providers** - Connect any data source via [Providers API](mirobody/pulse/theta/README.md) |
| 19 | - 🤖 **Custom Agents** - Create your own conversational agents via [Agents API](mirobody/pub/agents/README.md) |
| 20 | |
| 21 | **Health Data:** |
| 22 | |
| 23 | - 🏥 **FHIR & Health Standards** - 400+ health indicators, [LOINC / SNOMED CT / RxNorm cross-vocabulary search](mirobody/indicator/README.md) |
| 24 | - 📊 **Health Data Pipeline** - Ingest from [300+ wearables](mirobody/pulse/theta/README.md), [Apple Health](mirobody/pulse/apple/README.md), EHR; normalize to [StandardPulseData](mirobody/pulse/README.md) |
| 25 | |
| 26 | </div> |
| 27 | |
| 28 | --- |
| 29 | |
| 30 | ## 📖 Table of Contents |
| 31 | |
| 32 | - [Why Mirobody?](#-why-mirobody) |
| 33 | - [Architecture](#%EF%B8%8F-architecture) — AI & Agent Engine, FHIR & Health Standards, Health Data Pipeline, Infrastructure |
| 34 | - [Theta Wellness: Our Health Intelligence App](#-theta-wellness-our-health-intelligence-app) |
| 35 | - [Quick Start](#-quick-start) |
| 36 | - [Access & Authentication](#-access--authentication) |
| 37 | - [API Reference](#-api-reference) |
| 38 | - [Documentation](#-documentation) |
| 39 | |
| 40 | --- |
| 41 | |
| 42 | ## ✨ Why Mirobody? |
| 43 | |
| 44 | ### 🔄 Write Tools Once, Run Everywhere |
| 45 | |
| 46 | Forget about complex JSON schemas, manual bindings, or router configurations. In Mirobody, **your Python code is the only definition required.** |
| 47 | |
| 48 | - Tools built here instantly work in **ChatGPT** (via Apps-SDK) and the entire **MCP Ecosystem** (Claude, Cursor, IDEs). |
| 49 | - Mirobody works simultaneously as an **MCP Client** (to use tools) and an **OAuth-enabled MCP Server** (to provide data), creating a complete data loop. |
| 50 | - **🌐 HTTP Remote MCP Support**: Mirobody supports **HTTP-based remote MCP servers**, enabling cloud deployments and cross-network tool access. Configure `MCP_PUBLIC_URL` to expose your MCP server over HTTPS for ChatGPT Apps and other remote integrations. |
| 51 | |
| 52 | ### 💎 Your Data Is an Asset, Not a Payload |
| 53 | |
| 54 | Mirobody is built for **Personal Intelligence**, not just local storage. We believe the next frontier of AI is not knowing more about the world, but knowing more about *you*. |
| 55 | |
| 56 | - General AI creates generic answers. Mirobody uses your data to create a **Personal Knowledge Base**, enabling AI to give answers that are truly relevant to your life. |
| 57 | - You can run the entire engine **locally** on your machine. We provide the architecture to unlock your data's value without ever compromising ownership. |
| 58 | |
| 59 | ### 🤖 Native Agent Engine |
| 60 | |
| 61 | - Powered by a **self-developed agent engine** that fully reproduces **Claude Code's** autonomous capabilities locally. |
| 62 | - **🎯 Skills-Based Tool Development**: Mirobody supports developing tools using **Claude Agent Skills** format (SKILL.md files). You can create reusable tools that work seamlessly across the MCP ecosystem. Simply structure your tools as Skills and drop them into the `skills/` directory - Mirobody will automatically discover and expose them. |
| 63 | - Designed to load **Claude Agent Skills** SKILL.md files, turning your private data into an actionable knowledge base. |
| 64 | |
| 65 | ### 🧠 Agent Architecture |
| 66 | |
| 67 | Mirobody provides three agent types for different use cases: |
| 68 | |
| 69 | | Agent | Description | Use Case | |
| 70 | | ------------------- | -------------- |
People who liked this also viewed
6 picksType
- odoo-mcp-proAI connector for Odoo ERP | Connect Claude, ChatGPT, Cursor and other AI tools to Odoo via MCPMCP ServersJul 2026
- omnigentUniversal autonomous agent framework with ReAct loop, multi-provider LLM routing, reasoning graph, and MCP integration, domain-agnostic for building specialized AI agents.MCP ServersFeb 2026
- arxiv-mcp-serverAn MCP server that enables interacting with the arXiv API using natural languageMCP ServersAug 2025
- United States WeatherProvide real-time and forecast weather information for locations in the United States using natural language queries. Access current conditions, multi-day and hourly forecasts, weather alerts, and nearby weather stations without requiring aMCP Serversrecently
- mcp-server-demoDemo of MCP Server in Python using FastMCPMCP ServersAug 2025
- mcp-serverlearn to make some mcp serversMCP ServersMay 2025
