Pando

Documentation

One outline for you and your agents: what it is, how to start, and the two references.

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 and remembers in one bullet of your outline that you choose. A connector you approve, such as Claude or ChatGPT, starts with the whole outline, to read it, or to read and write it, as you choose when you approve it. Its reach can be narrowed afterwards to one bullet and everything under it: open that bullet, open Agents and API keys in Settings, tap the agent's row under Your agents, and press Let it reach only “…”, the bullet you are in, where the quotes hold that bullet's words. It then reads and writes there, even if you approved it read only, remembers there, and reaches nothing else in your outline. An agent you create there with Let it read and write this outline and Give it a bullet of its own to remember in unticked reaches nothing until you give it a bullet the same way; clients such as Claude Code, Codex or Cursor send its key as a bearer token. A bullet you protect refuses every agent's changes.

Getting started

Sign in and you are standing in your outline. Four ideas carry the rest:

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.