Documentation
What Pando is
Pando is an outline. Bullets sit inside bullets, each with one line of text and an optional note underneath for the detail. That is the whole data model, and it is enough: projects, lists, decisions, an agent's memory, all one tree.
The unusual part is who else works in it. An agent connects over MCP, gets a memory of its own that survives between sessions, and reads or writes exactly the branches you share with it. Nothing beside them.
Getting started
Sign in and you are standing in your outline. Four ideas carry the rest:
- Bullets. Every line is a bullet and bullets nest. Move them, reorder them, share a branch from any one of them.
- Notes. The line stays short; the note under it holds the detail. A note is stored and returned whole on every read, so nothing written there is ever shortened.
- Layouts. One property draws a bullet as a heading, a todo, code or a quote. Two arrange the bullets under it: a table draws children as rows and their children as cells, a board draws columns of cards. Set it back to bullet and the same content is an ordinary branch.
- Zoom. Any bullet can be the page. Zoom in and its line is the title; zoom out and it is one row again.
To connect an agent, the connect page walks Claude, Claude Code, ChatGPT or any other MCP client through it in about two minutes. For ready-made shapes such as GTD, PARA and the agent inbox, the template gallery copies a live branch into your outline with one press.
The references
MCP tool reference: every tool on the /mcp endpoint with its schema, generated from the same table the server answers tools/list with.
REST API reference: the /api/v1 doors for anything that speaks plain HTTP, with the same field vocabulary the server enforces.