automorphic-ai/aegis
Self-hardening firewall for large language models
This project helps protect large language models (LLMs) from harmful inputs and outputs, acting as a security layer for your AI applications. It takes user prompts and model responses, and flags potential threats like prompt injections, data leaks, or toxic language. The primary users are developers or operations teams responsible for deploying and managing LLM-powered applications, ensuring their safe and responsible operation.
267 stars. No commits in the last 6 months.
Use this if you are deploying a large language model and need to safeguard it and your users from various adversarial attacks and inappropriate content.
Not ideal if you are looking for a general-purpose content moderation tool or if your application does not involve large language models.
Stars
267
Forks
6
Language
Python
License
MIT
Category
Last pushed
Feb 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/automorphic-ai/aegis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ethz-spylab/agentdojo
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
guardrails-ai/guardrails
Adding guardrails to large language models.
JasonLovesDoggo/caddy-defender
Caddy module to block or manipulate requests originating from AIs or cloud services trying to...
deadbits/vigil-llm
⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language...
inkdust2021/VibeGuard
Uses just 1% memory while protecting 99% of your personal privacy.