bagel

View on GitHub

Query robotics, drone, and IoT data in plain English through an MCP server, with an intelligent edge data reduction pipeline that keeps only the data that matters.

★ 39730 forksPythonApache-2.0Extelligence-ai

Bagel is an MCP server that lets LLM clients query robotics, drone, and IoT data in plain English, translating questions into auditable DuckDB SQL over ROS1/ROS2/MCAP, PX4, ArduPilot, Betaflight, automotive, and live IoT formats. It also ships an edge data reduction pipeline that detects events on-device and keeps only

Use Cases

Query robotics, drone, and IoT logs in plain English via MCPSummarize ROS1/ROS2/MCAP bags and PX4/ArduPilot/Betaflight flight logsRun SQL over telemetry topics (peaks, moving averages, correlations)Author natural-language edge data reduction pipelines that keep only event windowsAnalyze live MQTT/Sparkplug B, PostgreSQL/TimescaleDB, and InfluxDB 3 streamsDetect anomalies like overheating IMUs or hard decelerations in recorded dataRun one pipeline across a whole fleet of logs and produce combined reportsShip kept data to S3/GCS/Azure as a pipeline step

Built With

Language: Python
Frameworks: MCP Python SDK · DuckDB · pandas · PyArrow · Pydantic · Uvicorn · FastMCP · Docker · ROS2 · MCAP · Ollama

bagel

Use Cases

Built With

Tags