SafellmHub/hguard-go

Guardrails for LLMs: detect and block hallucinated tool calls to improve safety and reliability.

21
/ 100
Experimental

This is a tool for developers who are building applications powered by large language models (LLMs). It helps ensure the LLM interacts safely and reliably with external tools by validating and enforcing rules on its 'tool calls'. Developers can define what tools an LLM can use, under what conditions, and what parameters are allowed, providing a safety net for AI integrations.

No commits in the last 6 months.

Use this if you are a developer building an LLM-powered application and need to prevent the LLM from making inappropriate, incorrect, or 'hallucinated' calls to external tools or APIs.

Not ideal if you are an end-user looking for a no-code solution to manage LLM behavior, or if you are not developing with Go.

AI-safety LLM-tooling Go-development API-governance AI-application-development
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

7

Forks

Language

Go

License

MIT

Last pushed

Jul 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/SafellmHub/hguard-go"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.