Masala (formerly Panel)
A research workspace where the agent can build its own panes
Masala, called Panel until September 2026, is a research workspace where an AI agent works beside you. Chat, files, PDFs and notebooks sit in one dock, and the agent can create custom viewers and apps when it needs them. It's an early build for testers. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49712621
✨ The overview, FAQ and details below were drafted by AI from the product's own website and haven't been reviewed by the maker yet. Are you the maker? Claim this listing to review and edit them.
Overview
Who is it for?
Researchers who read papers, analyze data and want an agent working in the same workspace.
Problem
Research work is spread across chat, PDF readers, notebooks and files, so an assistant only sees part of it.
Solution
One local workspace where the agent can read your files and build its own panes and modules, such as a literature review.
What makes it unique
The agent can create custom viewers and apps on the fly, and everything stays in local folders.
Masala (formerly Panel) FAQ
What do I need to run it?
Node 22.18+, pnpm, uv, and an agent CLI: Claude Code or Codex.
Where is my data stored?
Locally, in ~/Masala/masala.db and ~/Masala/workspaces.
Is it production-ready?
Not yet. It's an early build for testers, so expect rough edges.
Details
- Pricing
- Open Source
- Categories
- Research & DataAI Agents
- Built for
- Researchers
- Platforms
- Web
Hunted by AI Launch Team
Discussion (0)
Sign in to join the discussion.