guardrails
Risk detector
A Python framework for detecting and mitigating risks in large language models
Adding guardrails to large language models.
4k stars
25 watching
326 forks
Language: Python
last commit: about 1 month ago
Linked from 1 awesome list
aifoundation-modelgpt-3llmopenai
ethicalml/awesome-production-machine-learningRelated projects:
| Repository | Description | Stars |
|---|---|---|
 nvidia/nemo-guardrails | A toolkit for programmatically controlling output of large language models in conversational applications | 4,263 |
 guardrail-dev/guardrail | Generates code from OpenAPI/Swagger specifications for various Scala and Java frameworks | 527 |
 guidance-ai/guidance | An efficient programming paradigm for controlling large language models | 19,259 |
 gofireflyio/aiac | A tool that generates Infrastructure as Code templates and configurations using large language models. | 3,549 |
 bin123apple/autocoder | An AI model designed to generate and execute code automatically | 816 |
 trusted-ai/aif360 | A comprehensive toolkit for detecting and mitigating bias in machine learning models and datasets. | 2,483 |
| trusted-ai/adversarial-robustness-toolbox | A Python library that provides tools and techniques to defend against various attacks on machine learning models and applications. | 4,945 |
 flagai-open/flagai | An open-source toolkit for training and deploying large-scale AI models on various downstream tasks with multi-modality | 3,840 |
 aider-ai/aider | AI-powered pair programming tool for coding assistance and collaboration. | 23,297 |
 guardicore/monkey | An adversary emulation platform used to test and improve network security defenses by simulating malware infections | 6,697 |
 leptonai/leptonai | An AI service building framework using Python to simplify the development of machine learning models and services. | 2,669 |
 portkey-ai/gateway | A fast and secure routing service for integrating with large language models | 6,557 |
 protectai/llm-guard | A security toolkit designed to protect interactions with large language models from various threats and vulnerabilities. | 1,296 |
 salesforce/cloud-guardrails | A tool to rapidly apply hundreds of security controls in Azure using Terraform and Azure Policies | 183 |
 seldonio/alibi | A Python library for explaining machine learning models | 2,421 |