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
bytedance/trae-agent
Trae Agent is an advanced LLM-based agent designed for general-purpose software engineering tasks. It offers a powerful command-line interface (CLI) that understands natural language instructions and can execute complex software engineering workflows by leveraging various tools and multiple large language model (LLM) providers. The project is actively developed and aims to provide a transparent, modular architecture that is research-friendly, allowing researchers and developers to easily modify, extend, and analyze the agent. This makes it an ideal platform for studying AI agent architectures, conducting ablation studies, and developing novel agent capabilities. Trae Agent supports multiple LLM providers including OpenAI, Anthropic, Doubao, Azure, OpenRouter, Ollama, and Google Gemini APIs, enabling flexibility in model usage. It features a rich tool ecosystem that includes file editing, bash execution, sequential thinking, and more, facilitating diverse software engineering tasks. The agent also offers an interactive conversational mode for iterative development, detailed trajectory recording for debugging and analysis, and flexible JSON-based configuration with environment variable support. Installation is straightforward with pip and can be enhanced using the uv tool or make commands. Users can configure API keys via a JSON config file or environment variables, ensuring secure and convenient setup. The CLI provides commands for running tasks, interactive sessions, and configuration management, supporting various models and providers with customizable options such as working directories and trajectory saving. Trae Agent's design emphasizes ease of use, extensibility, and research utility, making it a valuable tool for both practical software engineering and AI research communities.
https://github.com/bytedance/trae-agent
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.