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
HKUDS/Auto-Deep-Research
Auto-Deep-Research is an open-source, fully automated personal AI assistant designed as a cost-efficient alternative to OpenAI's Deep Research. Built on the AutoAgent framework, it offers high performance, ranking as the top open-source method with comparable capabilities to OpenAI's Deep Research. The project supports a wide range of large language models (LLMs) including OpenAI, Anthropic, Deepseek, vLLM, Grok, and Huggingface, providing flexibility in interaction modes such as function-calling and non-function-calling LLMs. It enables users to handle file uploads for enhanced data interaction and offers a one-click launch experience with zero configuration required, making it accessible and easy to use. The project emphasizes cost efficiency by allowing users to utilize their own pay-as-you-go LLM API keys, avoiding the high subscription costs associated with commercial alternatives. Auto-Deep-Research is designed to be a community-driven tool, incorporating feedback to improve usability and expand compatibility. It serves as a demonstration of the AutoAgent framework's extensibility, showcasing how powerful agent applications can be rapidly developed. Installation is straightforward, with options for both direct setup and Docker containerization, which automatically adapts to the user's machine architecture. Users configure API keys for their preferred LLM providers through environment variables, supporting providers like Anthropic, OpenAI, Mistral, Google AI Studio's Gemini, and Huggingface. The project includes comprehensive documentation, community support via Slack and Discord, and links to research papers and benchmarks. Overall, Auto-Deep-Research offers an accessible, high-performance, and cost-effective AI assistant solution that empowers users to own and customize their personal AI research assistant without the constraints of expensive subscriptions or limited model support.
https://github.com/HKUDS/Auto-Deep-Research
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.
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.