kepano/obsidian-skills
Obsidian Skills provides a collection of agent skills enabling AI agents to interact with Obsidian vaults, facilitating content creation and editing of Markdown, Bases, and JSON Canvas files, as we...
Awesome AI Agents › AI Agent Development
NVIDIA-NeMo/Guardrails
NeMo Guardrails is an open-source toolkit developed by NVIDIA designed to add programmable guardrails to conversational systems powered by large language models (LLMs). These guardrails serve as control mechanisms that guide and restrict the behavior of LLMs in dialogue applications, ensuring safer, more trustworthy, and more secure interactions. The toolkit allows developers to define specific rules and constraints, such as preventing discussions on sensitive topics like politics, enforcing particular response styles, following predefined dialogue paths, and extracting structured data from conversations. The project is in beta and actively developed, with a focus on providing a robust framework for integrating guardrails between application code and LLMs. It supports multiple LLMs including OpenAI's GPT-3.5 and GPT-4, LLaMa-2, Falcon, Vicuna, and Mosaic, making it versatile for various conversational AI applications. NeMo Guardrails is designed to protect against common vulnerabilities in LLMs such as jailbreaks and prompt injections, enhancing the security and reliability of chatbots and virtual assistants. Key features include the ability to connect LLMs securely to other services, steer conversations along controlled paths, and enforce standard operating procedures within dialogues. The toolkit supports both synchronous and asynchronous APIs, facilitating easy integration into existing Python-based applications. It also offers different types of guardrails, including input rails that filter or modify user inputs, and dialog rails that influence how the LLM generates responses. Use cases for NeMo Guardrails span question answering systems, domain-specific assistants, LLM endpoints, and integration with frameworks like LangChain. The project emphasizes ease of use, requiring minimal code changes to add guardrails, and provides comprehensive documentation and examples to help developers get started. Overall, NeMo Guardrails aims to enhance the safety, control, and trustworthiness of LLM-based conversational systems.
https://github.com/NVIDIA-NeMo/Guardrails
Also in AI Agent Development
Panniantong/Agent-Reach
Agent-Reach allows AI agents to access web content from major social media and video platforms through a CLI, without API fees, enhancing their perceptual capabilities.
JCodesMore/ai-website-cloner-template
This project provides a reusable Next.js template for reverse-engineering and cloning any website into a modern codebase using various AI coding agents.
huggingface/smolagents
Smolagents is a minimalistic Python library by Hugging Face for creating intelligent agents that think and act by generating and executing Python code, supporting multiple LLMs, modalities, and tool integrations.
alibaba/page-agent
Page Agent is a JavaScript in-page GUI agent enabling natural language control of web interfaces without browser extensions or headless browsers, supporting various LLMs.
TencentCloud/TencentDB-Agent-Memory
TencentDB Agent Memory provides a local, 4-tier progressive pipeline for AI agent long-term memory, enhancing performance and reducing token usage without external API dependencies.
titanwings/distilly
A meta-skill that distills messages, documents, interviews and public sources about a person into a source-grounded Person Profile, packaged as an Agent Skill for coding agents and chat bots.
coze-dev/coze-studio
Coze Studio is an all-in-one AI agent development platform that simplifies the creation, debugging, and deployment of AI agents through visual tools and supports no-code and low-code development approaches.