Unplug AI

Security layer to protect LLM applications from attacks

---

Screenshots

---

Hunter's comment

Unplug is agent runtime security for LLM applications. It tracks where text came from (user vs retrieved vs tool output), scans for prompt injection and destructive actions, and enforces tool-call policy, with span-level redaction instead of binary blocking. Most guardrails nuke the whole message. Unplug finds the exact attack span and surgically removes it, keeping the rest usable.

---

Link

https://unplug-ai.org/

---

This is posted on Steemhunt - A place where you can dig products and earn STEEM.
View on Steemhunt.com