BigHugger
GH Repository · superagent-ai

superagent

Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

stars
6,749
30-day movement
+103/day
Related entries
60
Connections
2
otherprompt-injectionguardrailssecurityopenaiTypeScriptanthropicllmai

Superagent is a TypeScript library that adds guardrails to AI applications, protecting against prompt injections, data leaks, and harmful outputs. It embeds safety checks directly into your app and helps demonstrate compliance to customers.

You need to add security guardrails to an LLM-based application without building detection and filtering logic yourself.

Use it to

  • Block prompt injection attacks in LLM apps
  • Prevent sensitive data leaks in AI outputs
  • Filter harmful model responses
  • Demonstrate compliance to enterprise customers

For Developers building LLM applications that need safety guardrails

Role
other
Language
TypeScript
Licence
MIT
Forks
963
Open issues
9
Last push
2026-08-25
Latest release
v.0.0.1 · 2023-05-11
topicsaillmsecurityguardrailsprompt-injectionopenai