NeMo Guardrails
github.com
Toolkit for adding programmable guardrails to LLM-based conversational AI
Description
NeMo Guardrails is an open-source toolkit that allows developers to easily add programmable guardrails to LLM-based conversational applications. It provides a way to control and guide the output of large language models, enhancing safety, reliability, and functionality of AI chatbots and conversational agents
Features
INPUT RAILS
DIALOG RAILS
RETRIEVAL RAILS
EXECUTION RAILS, OUTPUT RAILS
CUSTOMIZABLE GUARDRAILS
MULTI-MODEL SUPPORT
COLANG SCRIPTING
Use cases
SAFETY ENHANCEMENT
TOPIC GUIDANCE
DETERMINISTIC DIALOGUE FLOWS
RAG INTEGRATION
CONVERSATIONAL AGENT DEVELOPMENT
Specs
| Type | Agent |
| Section | Agent frameworks |
| Pricing | free |
| Platform | Web + desktop |
| Systems | macos, cli, api, web |
| Site language | en |
| GitHub | nvidia/nemo-guardrails |
| Rating | 5.00 (1 reviews) |
| Views | 676 |
| Launched | 2024-09-02 |
