Bagel

Unlike cat videos, most data are trapped in the physical world. Bagel unlocks them and lets you chat with your physical data—just like you do with ChatGPT. For example:

Is my IMU sensor overheating?

Can’t wait to try it out? 👉 Check out the Quickstart.

🥯 Key Features

• Ask in plain language: No deep domain expertise needed.

• Transparent calculations: Deterministic SQL queries. No black-box LLM math.

• Natural-language pipelines: "Keep 10s around every hard brake, drop the rest" — one sentence becomes an auditable pipeline: previewed before a byte is written, then run once, across a fleet, or standing at the edge.

• Broad LLM support: Claude Code, Gemini, Cursor, Codex, and more.

• Dockerized environments: No local dependencies required.

• Extensible capabilities: Bagel can learn new tricks.

• Wide format coverage: Missing your data format? Open a ticket.

✅ Supported Data Formats

🆚 Bagel vs. the Tools You Already Use

You already have ros2 *, PlotJuggler, and grep. Bagel doesn't replace them — it answers the questions they make you work for, then hands off to them:

One sentence of plain language, one answer — instead of a pipeline of commands and a script you'll delete tomorrow. Here's a sentence becoming a data pipeline that reduces a bag around detected events:

Related MCP server: DuckDB MCP Server

💬 What Can I Prompt?

You can ask Bagel almost anything. For example:

What’s the correlation between current and voltage in the /spot/status/battery_states topic?

I think the robot hit a pothole. Can you check for sudden deceleration on the z-axis to confirm?

Can you help me tune the PID of my drone?

Time to put Bagel to the test: can it catch a drone doing barrel rolls? Spoiler: 🎉 It totally can.

💡 How Bagel Works

When you ask a question, Bagel analyzes your data source’s metadata and topics to build a high-level understanding.

Based on your prompt, if further inspection is needed, Bagel identifies the most relevant topics and interprets their meaning and structure. Bagel then writes the relevant topic messages to an Apache Arrow file and uses DuckDB to generate and execute queries against it.

This process is repeated as needed, running new queries until Bagel finds the best answer to your question.

LLMs excel at language but struggle with math. Bagel overcomes this by generating deterministic DuckDB SQL queries. These queries are displayed for you to audit, and you can guide Bagel to correct any errors.

⚡️ Quickstart

Three commands. That’s it.

📋 Prerequisites

Install Docker Desktop and Claude Code (or another MCP-enabled LLM).

1. Clone and start Bagel

git clone https://github.com/Extelligence-ai/bagel.git && cd bagel
docker compose run --service-ports ros2-kilted

Pick the service that matches your environment:

Wait for this output:

INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

2. Connect Claude Code

In a new terminal:

claude mcp add --transport sse bagel http://0.0.0.0:8000/sse

3. Prompt

claude

Summarize the metadata of the ROS2 bag "./data/sample/ros2/mcap".

That’s it — you’re chatting with your data.

🔒 Prefer fully offline?

Swap step 2 for a local model — your data and your LLM stay on the machine:

brew install ollama && ollama serve &                                  # or ollama.com
ollama pull qwen3:8b
uvx ollmcp --mcp-server-url http://localhost:8000/sse --model qwen3:8b

Model picks, expectations, and troubleshooting: Local LLMs guide.

Bagel works with any MCP-enabled LLM. Setup runbooks for tested alternatives:

• Claude Code (detailed guide)

• Gemini CLI

• Codex

• Cursor

• Copilot

Can’t find your LLM? Open a ticket.

🐶 Teach Bagel a New Trick

Bagel learns new capabilities through POML files—a structured set of instructions that describe a “trick,” such as computing latency statistics.

✍️ Create a .poml file

For example, let’s define ./src/agent/examples/woof.poml.

<poml>
    <task>
        Count the topics in the data source.
        If the count is odd, say "woof", else say "meow".
    </task>

    <output-format>
        Return the sound, the topic count, and a few cute emojis. Nothing else.
    </output-format>
</poml>

🗣️ Use the capability

Prompt Bagel:

Run the POML capability "./src/agent/examples/woof.poml" on the ROS2 bag "./data/sample/ros2/mcap".

Result:

meow 🐱 4 topics 🐱💤🎯

📚 Guides

• Natural-language pipelines — the model: a cadence, gates, and tasks; preview → run → save → batch → standing at the edge

• Event-driven data reduction — detect events, keep windows around them (snippets or one reduced bag), batch across fleets, upload to the cloud

• Live ROS2 robots over rosbridge — a step-by-step tutorial

• ROS text logs — inspect ~/.ros/log errors and warnings without opening a bag

• MQTT — live IoT topics, Sparkplug B, edge recording

• PostgreSQL / TimescaleDB — every table is a topic

• InfluxDB 3 — every measurement is a topic

• Automotive MDF4 & CAN (beta) — channel groups and DBC messages are topics; units ride along

• Local LLMs — fully offline with Ollama: your data and your model never leave the machine

📦 Integrations

• Rerun — "show me that event in Rerun": any time window as a ready-to-open recording

• Lichtblick / Foxglove — event windows as MCAP + pre-framed layouts for either viewer

• PlotJuggler — open Bagel's MCAP outputs directly; one-sentence pre-framed sessions, flattened CSV/Parquet exports

• Cloudini — Decode cloudini-compressed pointcloud data in pipelines

• Slack — pipelines post to your ops channel when they fire: "🚨 hard brake on {asset}"

• LeRobot (beta) — detected events become training episodes: a LeRobotDataset v3.0

🫶 Contributing

We’d love your help! The easiest way to support the project is by giving it a ⭐ on GitHub.

Other great ways to contribute:

• Request new features

• Report bugs

• Improve documentation

• Add new capabilities

Before contributing, please review the guidelines.

Join the conversation in our Discord server — we hang out there regularly.

📄 License

Bagel is open source under the Apache License 2.0.