DbSketch vs LLMSchema

DbSketch is a command-line generator for turning live relational database schemas into version-controlled documentation. It reads tables, columns, primary keys, and foreign keys from SQL Server, PostgreSQL, MySQL, and SQLite. Output choices are Graphviz DOT, Mermaid ER, or Markdown files with diagram text in a fenced code block. A YAML configuration holds one database connection and can define named diagram targets, allowing one setup to produce multiple focused diagrams with separate output and renderer settings. DbSketch can include native database comments where supported and apply YAML comment overrides. Its DOT renderer preserves foreign-key relationships down to the connected columns. The maker describes it as useful for repository documentation, CI, and compact schema snapshots for people and AI coding assistants. It is distributed as the.NET tool DimonSmart.DbSketch, which installs the dbsketch command; the getting-started guide requires the.NET 10 SDK. The software is MIT-licensed and costs nothing. It runs on Linux, macOS, and Windows and is self-hosted.

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.