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
snap-stanford/POPPER
POPPER is an advanced framework designed for automated hypothesis validation using agentic sequential falsifications, inspired by Karl Popper's principle of falsification. The project addresses the challenge of validating abstract, high-level hypotheses, especially those generated in large volumes by Large Language Models (LLMs), which are prone to hallucination and difficult to validate manually. POPPER employs LLM agents to design and execute falsification experiments that test the measurable implications of hypotheses. It features a novel sequential testing framework that ensures strict Type-I error control while actively gathering evidence from diverse observations, which can be drawn from existing data or newly conducted procedures. The framework has been demonstrated across six domains including biology, economics, and sociology, showing robust error control, high power, and scalability. POPPER achieves comparable performance to human scientists in validating complex biological hypotheses but with a tenfold reduction in time, offering a scalable and rigorous solution for hypothesis validation. The repository provides installation instructions, including environment setup and package installation via pip. It supports integration with local LLM servers such as vLLM, SGLang, and llama.cpp, provided they support OpenAI-compatible APIs. Users can run POPPER on their own hypotheses and datasets, with support for various data formats like CSV and PKL. The project includes demos, core API usage examples, and benchmark scripts to reproduce results from the associated research paper. POPPER also supports loading predefined biological and discovery-bench hypotheses for testing. Overall, POPPER is a cutting-edge tool for automating the scientific process of hypothesis testing, leveraging AI to enhance accuracy, efficiency, and scalability in research validation.
https://github.com/snap-stanford/POPPER
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.