Azimutt vs LLMSchema

Azimutt is a database exploration and documentation tool for understanding and managing databases. Its ERDs let users choose which tables, columns, relations, and ordering to show, while data exploration follows relations and can access real data on demand. For schema design, it provides AML, a minimal domain-specific language. Documentation includes table and column notes, layout memos, and visual indications; schema analysis can point out inconsistencies and possible improvements. Listed connectors cover PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, MongoDB, Couchbase, BigQuery, and Snowflake. Other schemas can be imported in JSON format, and the CLI includes JSON schema inference. The maker says schema parsing happens in the browser, projects can remain local, and Azimutt can be self-hosted. The free plan has no long-term save and allows a maximum of one user. Solo costs €7.00 per month billed annually; Team costs €35.00 per month billed annually per user. The site says Azimutt is made and hosted in the EU, while its privacy policy says personal data is hosted on DigitalOcean servers in the United States.

LLMSchema is free, MIT-licensed software that generates database schema documentation for LLMs and AI agents. It extracts relational schemas from PostgreSQL, MySQL, and SQLite, then documents tables, columns, types, indexes, constraints, and relationships in Markdown. The default output is one portable Markdown document. An alternate layout creates an overview plus a separate Markdown file for each table. Users can include selected tables or exclude tables from the generated documentation. LLMSchema is available as a command-line tool and a Go library, with installation instructions for Go and a quick install script for macOS and Linux. The README shows adding schema generation to a Makefile or migration script to keep documentation current. It also suggests pointing a coding agent to the schema files from AGENTS.md, CLAUDE.md, or an equivalent instruction file. The project is self-hosted and listed for Linux, macOS, and Windows. Its maker positions it for development databases and says not to rely on it for production-critical documentation.