hatchmoment. scored by care · not by stars

llm-safe-sql

Safely runs LLM‑generated UPDATE/DELETE statements, shows real before‑after diffs

notableTypeScript🗄 Data & Databases

The library lets a language model propose data‑modifying SQL, then executes it inside a transaction to capture exact before and after values before rolling back. Humans review the measured changes, ensuring the model’s intent matches reality before any permanent commit. It works with MySQL and PostgreSQL, requires no runtime dependencies, and isolates the approval step in a separate process for security. This approach prevents hidden side‑effects that static analysis can miss, making AI‑driven database agents safer.

ai-safetydatabasedry-runguardrailshuman-in-the-loopllmllm-agentmcpmcp-servermysqlpostgresqlrollbacksqltypescript
View on GitHub →

hyuga611/llm-safe-sql