Agents work from your context, with your tools.
Your notes, data, files, pages and code sit on one canvas. Agents from any vendor read it, use the tools you connect and put their work back on it.
-
Your context
Everything the work touches, on one canvas.
Notion pageTraining planDataros_sessions.jsonlPDFNemotron 3 reportCodetrain_lora.py -
An agent reads it
Any vendor, on your plan or your key.
Claude Code
Codex
Gemini CLI
Cursor
Local model
ROS
-
It uses your tools
Every agent gets the same tools.
Web search
Python sandbox
Notion
Google Drive
GitHub
Zotero
-
The work lands
On the canvas, with its source, its agent and its model.
Text · Finding Tool calls right 84%, up from 71% 3 backedClaude Code
See the whole picture.
Every source, search, run and answer is a block on the canvas. Each one shows where it came from, which agent made it and on which model.
ROSROS · Nemotron 3 Nano on Nebius Token Factorywriting eval_tools.py
Make the connections.
Put the plan next to the data. Group the evals. Link the chart to the claim it backs. The agents work from the connections you make.
Direct the work.
Ask ROS from the bar on the canvas. It plans the work and hands each task to the right agent. Changes arrive as proposals: accept, change or undo. You set how much lands without asking.
ROS runs on NVIDIA Nemotron 3: hosted free on Nebius Token Factory, or a 3 GB download on your Mac.
Fine-tune Nano on our sessions and check its tool callsYours, on your own machine.
Open source under MIT. It runs on your computer and talks only to the providers you choose.
- Your keys stay with you. Saved on your computer and sent only to their own provider.
- Use the agent plans you already have. Claude Code, Codex and the others sign in as they do today.
- Works offline. With local models and the local ROS.
- Plain files. Markdown, notebooks and CSV that other apps open too.
Run your agents in the open.
curl -fsSL https://ros-ai.io/install.sh | sh
Mac, Linux or Windows under WSL · Node 24 · From source