DietrichGebert/ponytail
Ponytail enables AI agents to generate more concise, efficient, and cost-effective code by enforcing a "lazy senior dev" methodology, prioritizing existing solutions and minimal implementation.
Awesome AI Agents › AI Assistants
tsinghua-fib-lab/AgentSquare
AgentSquare is the official implementation of the research paper titled "AgentSquare: Automatic LLM Agent Search in Modular Design Space," presented at ICLR 2025. This project focuses on automating the search for optimal large language model (LLM) agent designs within a modular design space. It provides code, prompts, and results that enable researchers and developers to explore and evaluate different LLM agent configurations efficiently. The repository includes demos, source code, and newly discovered modules that enhance the capabilities of LLM agents. The project supports various tasks such as ALFWorld, WebShop, M3Tooleval, and Sciworld, demonstrating its versatility in applying modular LLM agents to diverse environments. Users can quickly set up the environment, configure API keys, and run demos or other tasks with provided scripts. The modular design challenge encourages the community to contribute new standardized modules, fostering collaboration and innovation in LLM agent research. AgentSquare emphasizes a standardized I/O interface for agent modules, facilitating easy integration and experimentation. The repository offers detailed documentation on module interfaces and procedures for contributing new modules. This approach aims to consolidate collective efforts in the LLM agent research community, promoting the development of more effective and adaptable agents. Overall, AgentSquare serves as a comprehensive platform for automatic LLM agent design search, providing tools and resources to advance research and practical applications in this field. It is well-documented, actively maintained, and encourages community participation through module contributions and challenges.
https://github.com/tsinghua-fib-lab/AgentSquare
Also in AI Assistants
HKUDS/DeepTutor
DeepTutor is an AI-powered personalized learning assistant that offers interactive knowledge Q&A, visualization, practice generation, and deep research capabilities to enhance education through a comprehensive and adaptive platform.
agentscope-ai/QwenPaw
QwenPaw is a personal AI assistant framework that provides local or cloud deployment, multi-channel connectivity, skill extensibility, and multi-agent collaboration for enhanced productivity and cr...
mukul975/Anthropic-Cybersecurity-Skills
A comprehensive, open-source library of 754 structured cybersecurity skills for AI agents, mapped across five prominent industry frameworks.
googleworkspace/cli
gws is a command-line tool that dynamically interfaces with Google Workspace APIs (Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin) and includes AI agent skills for automation.
nanocoai/nanoclaw
NanoClaw is a lightweight, secure AI assistant platform that runs agents in isolated containers, providing a customizable alternative to OpenClaw with native Anthropic Claude Code integration and m...
assafelovic/gpt-researcher
GPT Researcher is an autonomous AI agent that conducts deep web and local research to generate detailed, unbiased research reports with citations.
screenpipe/screenpipe
Screenpipe transforms your computer into a personal, local, and private AI that records, searches, and automates based on all your digital activities.