Tuva is an AI research assistant built for computational science. It lives inside VS Code alongside your notebooks, papers, and data — and helps you read, write, and reason across all of them.
What it does
Chat with your project. Ask questions grounded in your notebooks, code, and the PDFs in your workspace. Citations link back to the exact cell or page.
Read papers faster. Index a folder of PDFs and Tuva builds a searchable knowledge base with author/summary aliases, so you can ask "what does the FORTE paper say about X" instead of hunting through tabs.
Work in notebooks. Tag cells, send outputs, errors, or figures straight to chat, and get help debugging or extending your analysis without leaving the notebook.
Use your own tools. Tuva exposes its retrieval and project context as MCP tools, so Claude Code, Codex, and other MCP-aware agents can use the same knowledge base.
Getting started
Install the extension and open the Tuva sidebar (or Cmd/Ctrl+Shift+T).
Sign in to enable cloud mode, or set entropy.mode to local and provide your own API key.
Open a folder with notebooks and/or PDFs — run Index Workspace from the command palette to build the knowledge index.
Start chatting.
Modes
Cloud (default): authenticated via Supabase, LLM calls go through Tuva's proxy.
Local: bring your own keys via .env, no auth required. Useful for offline or self-hosted workflows.
