hyuga
@hyuga611
Small, zero-dependency tools that check what an AI agent claims against what is actually there. Verification over description.
On GitHub since July 2024
1
Published Tools
0
Total Stars
0
Weekly Downloads
0
GitHub Followers
17
Public Repos
Published Tools
1 MCP Serveracross 1 category@hyuga/llm-safe-sql
hyuga611
Let an LLM propose UPDATE/DELETE, then actually run it, measure the real before/after diff, and always roll back — so the human approves measured facts, not the model's claim.
...moreMCP Servermcp
1 dir