superagent and AgentArmor

About superagent

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.

This helps secure your AI applications by protecting them from malicious inputs and ensuring sensitive data isn't leaked. You feed in user messages or documents, and it helps identify and block harmful prompts, remove personal information, and analyze codebases for AI-targeted threats. It's for anyone responsible for the security and compliance of AI systems, such as AI product managers or security engineers.

About AgentArmor

ankitlade12/AgentArmor

The full-stack safety layer for AI agents. Budget limits, prompt injection shields, PII filtering, output firewalls, and hooks — in 2 lines of code.