Features
Reactive execution: cells update on dependency change
Git-friendly plain Python (.py) storage
Built-in SQL cells: DuckDB, Postgres, MySQL, SQLite
Interactive UI widgets: sliders, dropdowns, tables, plots
AI autocomplete, chat, and error fixing
marimo pair: connect AI agents to running sessions
Deploy notebooks as WASM HTML or web apps
Run notebooks as Python scripts via CLI
Reproducible deterministic execution, no hidden state
Package requirements embedded in notebook file
VS Code and Cursor extension for IDE integration
MCP support for AI agent connectivity
JupyterHub extension for enterprise deployment
Customizable UI with themes and vim keybindings
Debugging panels and profiler
Live knowledge graph from code, commits, issues, and docs
Feasibility analysis: flags buildable vs risky items
Technical design document generation grounded in service topology
Impact assessment maps services, APIs, and dependencies across repos
Auto-scoping epics into Jira/Linear stories with effort estimates
One-shot production code generation grounded in service patterns
AI code reviews with cross-repo impact analysis
Production issue triage via MCP
Conversational learning from Slack and Jira
Accelerated onboarding via system-level Q&A in coding agents
Create Jira tickets and merge requests from Slack
MCP server for integration with Cursor, Claude Code, Codex
On-prem or cloud deployment
No code storage or model training
