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
assafelovic/gpt-researcher
GPT Researcher is an open deep research agent designed to autonomously conduct comprehensive research on any topic by leveraging both web and local document sources. It generates detailed, factual, and unbiased research reports complete with citations. The project addresses common challenges in manual and AI-assisted research such as misinformation, outdated data, token limitations, and bias by using a multi-agent architecture inspired by recent AI research papers like Plan-and-Solve and Retrieval-Augmented Generation (RAG). The architecture involves a planner agent that formulates research questions and multiple execution agents that gather relevant information from diverse sources. These findings are then aggregated by a publisher agent into a comprehensive report. GPT Researcher supports deep recursive research workflows with tree-like exploration patterns, enabling in-depth and broad topic coverage with concurrent processing for speed and smart context management. It can generate reports exceeding 2,000 words, aggregate information from over 20 sources, and supports smart image scraping and filtering. The project offers a frontend in lightweight HTML/CSS/JS and a production-ready NextJS + Tailwind version. It supports JavaScript-enabled web scraping and maintains memory and context throughout the research process. Reports can be exported in multiple formats including PDF and Word. The project is accessible via Python package, Docker, and includes extensive documentation, tutorials, and live demos. It aims to empower individuals and organizations with accurate, unbiased, and factual information through AI-driven research automation.
https://github.com/assafelovic/gpt-researcher
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...
screenpipe/screenpipe
Screenpipe transforms your computer into a personal, local, and private AI that records, searches, and automates based on all your digital activities.
agent0ai/agent-zero
Agent Zero is a dynamic, customizable AI framework that acts as a personal assistant capable of learning, creating tools, and cooperating with multiple agents to accomplish diverse tasks.