\nTechnical Paper |\nDocumentation |\nX\n
\n\n**OpenMind's OM1 is a modular AI runtime that empowers developers to create and deploy multimodal AI agents across digital environments and physical robots**, including Humanoids, Phone Apps, Quadrupeds, educational robots such as TurtleBot 4, and simulators like Gazebo and Isaac Sim. OM1 agents can process diverse inputs like web data, social media, camera feeds, and LIDAR, while enabling physical actions including motion, autonomous navigation, and natural conversations. The goal of OM1 is to make it easy to create highly capable human-focused robots, that are easy to upgrade and (re)configure to accommodate different physical form factors.\n\n## Pick Your Runtime\n\nOM1 was originally built in Python, and the Go runtime is a newer, performance-focused implementation. We migrated to Go for lower latency, better performance, efficient concurrency, a smaller memory footprint for edge devices, and simpler deployment as a single Go binary (with the Zenoh C library bundled alongside it).\n\nThe Go runtime covers the core agent pipeline, but several capabilities available in the Python runtime are still under active development. For most new development we recommend the Go runtime.\n\n> [!NOTE]\n> However, **Python** version is available at [`python`](https://github.com/OpenMind/OM1/tree/python) for use, if preferred. It is now deprecated and will not be maintained.\n\n## Capabilities of OM1\n\n* **Modular Architecture**: Written in Go for performance and seamless integration.\n* **Data Input**: Easily handles new data and sensors.\n* **Hardware Support via Plugins**: Supports new hardware through plugins for API endpoints and specific robot hardware connections to `ROS2`, `Zenoh`, and `CycloneDDS`. (We recommend `Zenoh` for all new development).\n* **Pre-configured Endpoints**: Supports Text-to-Speech, multiple LLMs from OpenAI, xAI, DeepSeek, Anthropic, Meta, Gemini, NearAI, Ollama (local), and multiple Visual Language Models (VLMs) with pre-configured endpoints for each service.\n* **Metrics & Observability**: Includes a pre-configured Prometheus and Grafana stack to monitor real-time AI pipeline metrics like LLM and ASR latencies.\n\n## Architecture Overview\n\n\n## Getting Started\n\nIf you are new to OM1, this is the fastest path to a successful first run using the `conversation` agent.\n\nThe conversation agent uses your webcam and microphone to enable natural voice interactions with an AI. The model processes visual and audio inputs and responds through speech.\n\nThis quick start uses the default starter configuration to help you understand the OM1 pipeline. It visualizes state updates in the terminal and demonstrates the input-LLM-action flow.\n\n### Quick Start (5 Minutes)\n\n1. Install system dependencies.\n2. Download the binary or clone the repository.\n3. Add your OpenMind API key.\n4. Launch OM1 and verify it is running.\n\n### 1. Install System Dependencies\n\nFor macOS:\n```bash\nbrew install portaudio ffmpeg\n```\n\nFor Linux:\n```bash\nsudo apt-get update\nsudo apt-get install -y portaudio19-dev ffmpeg\n```\n\n> [!TIP]\n> Webcam access is recommended if configuring VLM.\n\n### 2. Download or Build\n\n#### Option A: Download Pre-built Binary (Recommended)\n\nNo Go installation required. Download the latest release for your platform from the [Releases page](https://github.com/OpenMind/OM1/releases).\n\nCurrent pre-built binaries are available for:\n\n- `linux-amd64`\n- `linux-arm64`\n- `darwin-arm64`\n- `darwin-amd64`\n\nAfter downloading and extracting the archive, open a terminal in the extracted folder and run:\n\n```bash\nchmod +x om1\n./om1 config =