bytedance/deer-flow
DeerFlow is a community-driven deep research framework that integrates language models with web search, crawling, and Python execution tools to facilitate comprehensive AI-powered research workflows.
Awesome AI Agents › Reasoning Frameworks
AgentEra/Agently-Daily-News-Collector
Agently-Daily-News-Collector is an open-source project that showcases an automated daily news collection workflow powered by the Agently AI application development framework. The project leverages large language models (LLMs) to automatically gather, summarize, and compile news on any user-specified topic into high-quality markdown and PDF files. Users simply input the topic of interest, and the AI agents handle the entire process of searching, filtering, summarizing, and organizing news content. The system supports customization through a YAML settings file where users can configure API keys and other parameters to tailor the news collection process. The project is implemented in Python and requires installation of dependencies listed in a requirements file. It uses several key libraries including duckduckgo-search for retrieving news, BeautifulSoup4 for parsing web content, and PyYAML for configuration management. The workflow involves generating an outline for the news report, searching for relevant news articles, summarizing selected articles, and compiling the results into a structured news collection file. The project provides example output files demonstrating the format and quality of the generated news collections. It is designed to be user-friendly, requiring minimal input and automating the complex task of news aggregation and summarization. The repository also includes detailed instructions for setup and usage, along with links to the Agently framework for users interested in the underlying AI application development technology. Community support is available through issue reporting, email contact, and social channels like Discord and WeChat groups. Overall, Agently-Daily-News-Collector offers a powerful and flexible solution for automated news collection and summarization using AI agents, suitable for users who want to stay updated on specific topics without manual effort.
https://github.com/AgentEra/Agently-Daily-News-Collector
Also in Reasoning Frameworks
VectifyAI/PageIndex
PageIndex is a reasoning-based document indexing and retrieval system that uses a hierarchical tree structure to enable human-like, vectorless retrieval and multi-step reasoning over long professional documents.
guidance-ai/guidance
Guidance is a programming paradigm and library that enables efficient and fine-grained control over large language models to produce structured, high-quality outputs with reduced latency and cost.
friuns2/BlackFriday-GPTs-Prompts
A curated repository of free GPT prompts and jailbreaks across various domains, enabling users to utilize GPT models without a subscription to GPT Plus.
refly-ai/refly
Refly is an open-source AI-native creation engine that combines multi-threaded dialogues, multimodal inputs, knowledge base integration, and AI-powered tools to transform ideas into production-ready interactive content and web applications.
mongodb-developer/GenAI-Showcase
MongoDB's GenAI Showcase is a comprehensive repository offering examples and applications that integrate MongoDB with advanced Generative AI techniques like Retrieval-Augmented Generation and AI Agents to support AI development and innovation.
anysphere/priompt
Priompt is a JSX-based prompting library that uses a priority system to efficiently construct token-limited prompts for language models, inspired by React's component design.
HKUDS/Auto-Deep-Research
Auto-Deep-Research is an open-source, fully automated, and cost-effective personal AI assistant that supports multiple large language models and offers a one-click launch experience as an alternative to OpenAI's Deep Research.