...
- AI in the notebook: Chat with AI assistants and run agents directly inside JupyterLab, powered by various model providers.
- Targeted coding help: Ask the AI to write code, explain complex sections, or fix errors within a specific notebook or a single cell.
- Agents and a secure gateway: Run AI agents on the platform through a single, trusted entry point. For safety, some workflows require human approval before taking action.
- The AI Registry in JupyterLab: Access a hub of NASA-validated AI building blocks—including MCP servers, skills, agents, models, prompts, and harnesses. Use the AgentRegistry panel to search, deploy, and equip your AI assistant with these tools. (Currently rolling out to all projects; See the tool reference.
- Model endpoints on demand: Import and call your own custom models, or connect to managed models, directly from your notebook.
Working Together
- Real-Time Co-Editing: Edit the same notebooks and files at the exact same time as your teammates. Markers show who is online, and everything saves to your shared space.
- Easy Activation: Project admins can turn this feature on instantly in the RPAdmin console without contacting support.
See Working together on the same notebook.
...
Cost Visibility & Tracking
- Your Own Usage: View your personal compute/storage usage and remaining budget right inside JupyterLab.
- The Big Picture: Project admins can track the entire team's spending against the budget from the RPAdmin console.
The RPAdmin console — self-service for project admins
...