LLMSchema
github.com
What it is
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.
Spec sheet
- Purpose
- LLMSchema generates database schema documentation for LLMs and AI agents.Read 8 Oct 2026 · github.com
- License
- The repository identifies the project as MIT licensed.Read 8 Oct 2026 · github.com
- Maker
- The repository is published under the GitHub account tordrt, whose profile name is Tord.Read 8 Oct 2026 · github.com
- AI agent setup
- The README suggests telling a coding agent where the schema docs are located in AGENTS.md, CLAUDE.md, or an equivalent instruction file.Read 8 Oct 2026 · github.com
- Contribution and support
- The README invites contributions through issues and pull requests and suggests opening an issue first for larger features.Read 8 Oct 2026 · github.com
- Developer interface
- LLMSchema is available as a command-line tool and a Go library.Read 8 Oct 2026 · github.com
- Feature gaps
- The README lists views and materialized views, PostgreSQL triggers and functions, and table and column comments as areas to explore.Read 8 Oct 2026 · github.com
- Filtering
- Users can include selected tables or exclude tables from the generated documentation.Read 8 Oct 2026 · github.com
- Installation
- The README provides Go installation instructions and a quick install script for macOS and Linux.Read 8 Oct 2026 · github.com
- Integration
- The README shows adding schema generation to a Makefile or migration script to keep documentation up to date.Read 8 Oct 2026 · github.com
- Intended use
- The maker describes the tool as intended for development databases to support AI-assisted coding and says not to rely on it for production-critical documentation.Read 8 Oct 2026 · github.com
- Interfaces
- LLMSchema is available as a command-line tool and as a Go library.Read 8 Oct 2026 · github.com
- Output
- It documents tables, columns, types, indexes, constraints, and relationships in Markdown.Read 8 Oct 2026 · github.com
- Output formats
- It can produce one portable Markdown document or an overview with a separate Markdown file for each table.Read 8 Oct 2026 · github.com
- Output options
- It writes one Markdown document by default and can optionally create an overview plus one file per table.Read 8 Oct 2026 · github.com
- Pricing and trial
- The README provides installation instructions without listing paid plans or a trial.Read 8 Oct 2026 · github.com
- Schema details
- The generated documentation can include tables, columns, types, indexes, constraints, and relationships.Read 8 Oct 2026 · github.com
- Security and reliability limit
- The README says the tool is intended for development databases and should not be relied on for production-critical documentation.Read 8 Oct 2026 · github.com
- Supported databases
- It extracts schemas from PostgreSQL, MySQL, and SQLite.Read 8 Oct 2026 · github.com
Plans and prices
Strong points and limits
Strong points
- Free MIT-licensed software
- Supports PostgreSQL, MySQL, and SQLite
- Offers CLI and Go library interfaces
- Can include or exclude selected tables
- Markdown output supports one file or per-table files
Limits
- Not intended for production-critical documentation
- Views and materialized views are feature gaps
- PostgreSQL triggers and functions are areas to explore
Who it suits
LLMSchema suits developers maintaining schema context for AI-assisted coding. It is intended for development databases and self-hosted workflows on the listed operating systems.
Verdict
LLMSchema gives developers a focused, self-hosted way to turn relational schemas into Markdown context for AI tools. Its database coverage and output choices are clear, with documented limits around production use and additional schema features.
Where Specifiction places it
- Database Documentation Tools#11 of 278.1