Skip to main content

Context for agents

Bauplan can be used with any LLM or IDE assistant without installing an MCP server or a plugin. Because the whole platform is code-first (a CLI and a Python SDK) and the documentation is published in LLM-friendly formats, the assistant can read the docs. This is often the simplest starting point.

Repository context

A CLAUDE.md file at your project root tells the assistant how to work with Bauplan before it writes any code: how to authenticate, the branch-based workflow, CLI and SDK conventions, and the safety rules to follow. Drop the maintained version into your project with:

curl -o CLAUDE.md https://raw.githubusercontent.com/BauplanLabs/bauplan-skills/main/CLAUDE.md
note

Depending on the AI coding tool of your choice, this file might follow a different naming convention. For instance, both Codex and Cursor adopt AGENTS.md instead of CLAUDE.md. No modification other than renaming the file is required!

Feeding documentation to LLMs

Bauplan's documentation is published in formats meant to be read by models, not just people:

  • llms.txt is a single-page index of the documentation following the llms.txt convention, small enough to fit in a single context window.
  • Markdown version of any page: append .md to any documentation URL to get a plain Markdown version. For example, https://docs.bauplanlabs.com/agents/overview becomes https://docs.bauplanlabs.com/agents/overview.md. This is useful for pasting a specific page into an assistant as context.
  • The full CLI and SDK reference as Markdown: the entire API reference is available as two self-contained Markdown files, reference/cli.md and reference/bauplan.md. Feeding these two files to an agent gives it the complete, authoritative syntax of every command and SDK method in one shot, which sharply reduces hallucinated flags and arguments when it generates code.