Busabase

Bring Your Own Agent

Connect any coding agent — Claude Code, Cursor, Codex — to drive Busabase. One prompt to onboard, one command to install a permanent skill.

Bring Your Own Agent

Busabase has no built-in model. Instead it speaks plain HTTP, so you point your own agent at it — Claude Code, Cursor, Codex, Gemini CLI, or anything that can call a REST API. The agent proposes changes as Change Requests; you stay the one who approves and merges.

You connect in two moves: paste one prompt to onboard, then install a permanent skill so the agent just knows Busabase every session.

The Agent Integration panel — copy one prompt to point any agent at this workspace.

Dashboard → Agent Skills: copy the prompt (it's localized to your UI language), or grab the MCP / OpenAPI endpoints.

Onboard with one prompt

Copy the prompt and paste it into your agent

Open Agent Skills in the dashboard sidebar and copy the short prompt. It points your agent at this workspace's live SETUP_SKILL.md — a self-contained onboarding script — and tells it to reply in your language and never merge without your approval.

The agent welcomes you and asks what to manage

Instead of dumping commands, it opens with a short welcome — what Busabase is, why the review gate matters — and asks "what do you want to manage?" Answer in a sentence (e.g. "my sales leads / a CRM").

It connects and saves your config

The agent finds or creates an API key, verifies it can read your workspace, and writes the base URL + key to ~/.busabase/.env so every future session — and the installed skill — can read it. (See API Tokens to create a key yourself.)

It sketches the structure, you confirm, then it builds

Before creating anything, the agent shows you the planned shape — folders, bases, fields, relations — and waits for your go-ahead. On approval it creates the bases (always more than one node, so the workspace never opens empty) and you can see them in Graph View.

Graph View — the structure the agent proposed, made concrete.

It seeds sample records — and you approve the first one together

The agent submits a few starter records as Change Requests (never written directly). It walks you through approving and merging the first one from the Inbox, so you watch the propose → review → merge loop close end to end.

The Inbox — every AI submission waits here for your review.

Install the skill for everyday use

Onboarding ends by installing a small, permanent busabase skill, so you never re-paste the prompt again:

npx skills add busabase/skills

The generic skills CLI detects your agent (Claude Code, Cursor, …) and installs it globally. The skill is thin and evergreen — it reads ~/.busabase/.env and points at your live API for the full surface, so it never goes stale.

Setting up a brand-new workspace? The Quick Start walks you through the UI-first version (sign up → approve your first record) in ~5 minutes. This page is for handing the wheel to an agent.

Everyday: three ways to talk to it

Once connected, pick whichever fits the task — all three read the same ~/.busabase/.env:

MethodBest for
busabase-cliThe ergonomic everyday loop: npx busabase-cli bases list, change-requests review --change-request-id <id> --verdict approved, change-requests merge --change-request-id <id>.
curlQuick, zero-install calls against /api/v1.
MCP / OpenAPIThe complete, current surface — connect over MCP, or read /api/v1/openapi.json.

MCP endpoint — connect any MCP-capable agent or IDE.

The loop never changes: list → propose a Change Request → you review → merge → read back. Never bypass review unless you explicitly ask for a direct merge.

See also: Core Concepts · Quick Start · AI Comments & @AI · REST API

On this page