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
coze-dev/coze-loop
Coze Loop is a next-generation AI agent optimization platform designed to streamline the entire lifecycle of AI agent development and operation. It offers a comprehensive suite of tools and features that support developers from the initial stages of prompt engineering through debugging, evaluation, and monitoring after deployment. The platform is developer-oriented and provides full-lifecycle management capabilities, addressing common challenges in AI agent development such as prompt creation, performance evaluation, and operational monitoring. The platform includes a prompt development module that facilitates writing, debugging, optimizing, and version managing prompts. It features a visual Playground for real-time interactive testing and comparison of outputs from different large language models (LLMs). This helps developers intuitively understand and improve prompt effectiveness. Coze Loop also offers a robust evaluation module that enables systematic, multi-dimensional automated testing of AI agent outputs. This includes assessments of accuracy, conciseness, and compliance, helping ensure the quality and reliability of AI agents. For operational monitoring, Coze Loop provides visual observation tools that track the entire execution process of AI agents. It records every step from user input to AI output, including key nodes like prompt parsing, model invocation, and tool execution. The platform automatically captures intermediate results and flags abnormal states, aiding in troubleshooting and optimization. The platform supports integration with various AI models, including OpenAI and Volcengine Ark, through a flexible model configuration system. It is available as an open-source edition, allowing developers to freely access core foundational features, customize, and extend the platform to meet specific business needs. This open-source approach fosters community collaboration and innovation in AI agent development. Coze Loop is designed for easy deployment using Docker and Docker Compose, with detailed documentation and developer guides available to assist with installation, configuration, and secondary development. It is licensed under Apache 2.0 and encourages community contributions, making it a collaborative and evolving tool for AI agent optimization.
https://github.com/coze-dev/coze-loop
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.