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
huggingface/smolagents
The project "smolagents" by Hugging Face is a lightweight and minimalistic Python library designed to create intelligent agents that think and act by writing and executing Python code. The library emphasizes simplicity, with the core logic contained in about 1,000 lines of code, making it accessible and easy to understand. It supports the creation of Code Agents, which generate their actions as executable Python code snippets, enabling dynamic and flexible agent behavior. To ensure security, these code actions can be run in sandboxed environments using tools like E2B or Docker. Smolagents is model-agnostic, meaning it can work with any large language model (LLM), including local transformer models, OpenAI, Anthropic, and many others through integrations like LiteLLM and Hugging Face's InferenceClientModel. This flexibility allows users to choose their preferred LLM provider or model. The library also supports multiple input modalities such as text, vision, video, and audio, broadening the scope of applications. The library integrates seamlessly with the Hugging Face Hub, allowing users to share and pull tools and agents easily. It supports tools from various ecosystems, including LangChain, MCP, and Hugging Face Spaces, making it highly extensible. Users can run agents from the command line using provided CLI commands like "smolagent" for general multi-step agents and "webagent" for web browsing tasks. The project includes comprehensive documentation and tutorials, demonstrating how to define agents, equip them with tools, and run them with just a few lines of code. It also provides examples of how to connect to different LLM providers and how to share agents on the Hugging Face Hub. Overall, smolagents offers a powerful yet simple framework for building intelligent agents that operate by generating and executing Python code, suitable for a wide range of AI applications.
https://github.com/huggingface/smolagents
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.
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.
KKKKhazix/khazix-skills
Khazix Skills is an open-source collection of AI agent skills, including tools for disk analysis, AI news retrieval, project documentation tidying, and report generation, compliant with the Agent S...