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
Technion-Kishony-lab/data-to-paper
The 'data-to-paper' project is an innovative automation framework designed to facilitate end-to-end scientific research driven by AI, specifically large language models (LLMs). It systematically guides interacting AI agents through the entire scientific research process, starting from raw data and culminating in the creation of transparent, backward-traceable, and human-verifiable scientific papers. This framework is field-agnostic, meaning it can be applied across various scientific disciplines. Key features include the ability to trace every numeric value in the research paper back to the specific code lines that generated them, ensuring full transparency and verifiability. The platform supports both fully autonomous operation and human-guided research through a Copilot App, which allows users to oversee, inspect, guide the research, set goals, review AI-generated content, rewind steps, and track API costs. The system incorporates coding guardrails to minimize common errors in AI-generated code, particularly in statistical analysis. The motivation behind 'data-to-paper' is to establish a new standard for AI-driven research that maintains scientific rigor, transparency, and traceability while accelerating the research process. The implementation involves a combination of LLM and rule-based agents that perform tasks such as data exploration, literature search, hypothesis generation, data analysis, interpretation, and manuscript writing. The project is supported by published research papers and preprints that detail its methodology and capabilities. It has been tested on various datasets, including health indicators, social network data, and treatment policy datasets, demonstrating its versatility and effectiveness. The project invites contributions and feedback to extend its capabilities and adapt it to more complex research questions and datasets. Overall, 'data-to-paper' represents a significant advancement in automating scientific research with AI, emphasizing transparency, traceability, and human oversight.
https://github.com/Technion-Kishony-lab/data-to-paper
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.