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
mongodb-developer/GenAI-Showcase
MongoDB's GenAI Showcase is a comprehensive repository designed to support developers at all stages of their Generative AI journey. It offers an extensive collection of examples and sample applications that demonstrate the integration of MongoDB with advanced Generative AI techniques such as Retrieval-Augmented Generation (RAG) and AI Agents. The repository serves as a valuable resource for building industry-specific AI use cases by showcasing how MongoDB can function as a vector database, operational database, and memory provider within AI pipelines. The repository is organized into several key folders: 'notebooks' contains Jupyter notebook examples that cover RAG, agentic applications, and evaluation methods; 'apps' includes JavaScript and Python applications and demos that illustrate practical implementations; and 'partners' features contributions from AI partners, enriching the repository with diverse perspectives and solutions. To utilize the resources in this repository, users need to connect to a MongoDB cluster, which can be set up through MongoDB Atlas, a cloud database service. The repository provides clear instructions for registering an account, creating a database cluster, and obtaining the necessary connection string to enable seamless integration. The project encourages community involvement and contributions, supported by detailed contribution guidelines. It is licensed under the MIT License, promoting open collaboration and use. For users seeking assistance, the repository offers a dedicated issue tracker and links to additional resources such as the AI Learning Hub, GenAI Community Forum, and official MongoDB tutorials and code examples. Overall, MongoDB's GenAI Showcase is a robust and practical toolkit for developers aiming to leverage MongoDB in the development of cutting-edge Generative AI applications, providing both foundational knowledge and advanced examples to accelerate AI innovation.
https://github.com/mongodb-developer/GenAI-Showcase
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.
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.
NirDiamant/Controllable-RAG-Agent
Controllable-RAG-Agent is an advanced Retrieval-Augmented Generation solution featuring a deterministic graph-based autonomous agent designed for complex question answering with multi-step reasoning and hallucination prevention.