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
areal-project/AReaL
AReaL (A Large-Scale Asynchronous Reinforcement Learning System) is an open-source project providing a robust infrastructure for reinforcement learning, specifically tailored to bridge the gap between foundation model training and modern agent-based applications. Developed by researchers from Tsinghua IIIS and Ant Group, AReaL leverages a fully asynchronous RL training paradigm to achieve high efficiency and scalability, making it ideal for large-scale reasoning and agentic model development. The system emphasizes accessibility, efficiency, and cost-effectiveness for developers and researchers building AI agents. Key highlights include its flexibility for agentic RL and online RL training, supporting customization for black-box agent applications by simply modifying a `base_url`. It boasts industry-leading speed through stable, fully asynchronous RL training and has demonstrated cutting-edge performance in various applications, including math, coding, search, and customer service agents. AReaL continuously integrates new features and improvements, such as integration with NVIDIA's Scaffoldings for agentic RL training, support for Ascend NPU devices, and advanced components like AReaL-SEA for self-evolving data synthesis. It also offers AReaL-lite, a lightweight version for rapid prototyping and algorithm development, prioritizing ease of use with an algorithm-first API. The project aims to simplify multi-turn agentic RL training setups, offering significant speedups while maintaining or exceeding the performance of synchronous systems.
https://github.com/areal-project/AReaL
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.