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
oneil512/INSIGHT
INSIGHT is an autonomous AI system designed specifically for conducting medical research. It operates through a multi-agent architecture consisting of a boss agent and worker agents. The boss agent is responsible for managing the overall research objective by creating and prioritizing a task list based on an executive summary of completed tasks and their results. Worker agents then pick tasks from this list, execute them, and save the results to a Llama Index database. This index serves as a knowledge base that provides context to the workers and helps the boss agent in decision-making and task reprioritization. The system integrates with external APIs such as PubMed and MyGene, allowing it to access vast biomedical data resources to support its research tasks. The workers can query these APIs to gather relevant information, which is then processed and stored in the Llama Index. INSIGHT also supports reloading and continuing previous runs, enabling long-term research projects to be conducted incrementally. Additionally, it can load and utilize any human-readable data files alongside its findings, enhancing its data integration capabilities. Users can interact with the Llama Index directly through a provided script (`talk_to_index.py`), which allows querying the indexed data with arbitrary questions. This feature facilitates exploration and analysis of the accumulated research data. The output of INSIGHT includes detailed results for each task, stored in a structured directory format, and a comprehensive markdown file summarizing key findings. This summary includes high-level overviews, main points, key insights, creative hypotheses, and suggested research directions, providing a valuable resource for medical researchers. Overall, INSIGHT automates and streamlines the medical research process by leveraging AI agents, external biomedical APIs, and an indexed knowledge base, making it a powerful tool for advancing medical knowledge and discovery.
https://github.com/oneil512/INSIGHT
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.