Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
-
Updated
Dec 13, 2025 - TypeScript
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
拼好RAG:手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索;整合DeepSearch技术实现私域RAG的推理;自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construction and search. Combine DeepSearch for private RAG reasoning. Create a custom evaluation framework for GraphRAG.
[NeurIPS 2025] 🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability
Interact with the Deep Search platform for new knowledge explorations and discoveries
Turn topics into essays in seconds!
An implementation of Google Deep Search 🕵️ with support for 1000+ references, local inference, chatting with your scraping session using RAPTOR, and report generation.
A deep research framework based on progressive search and cross-evaluation.
A full-stack web application that conducts comprehensive research using multiple specialized AI agents to gather, analyze, and synthesize information from diverse sources into coherent reports.
HyDRA: Hybrid Dynamic RAG Agents, An advanced, agentic AI framework that transforms Retrieval-Augmented Generation from a static pipeline into a dynamic, learning reasoning system.
A collection of recipes to do the most with Valyu. Everything about search for AI agents.
Awesome Deep Research Implementations
How about a CLI for searching PDFs and Web for your Research
An open-source alternative to OpenAI Deep Research, combining web searching, content crawling, and AI-driven synthesis for in-depth topic exploration
🔍 Automate digital footprint analysis with DeepSearch, using advanced Google search operators to gather insights from multiple platforms efficiently.
Local DeepResearch, An AI-driven research system that performs comprehensive, iterative research on any topic using whatever LLM you want!
一个基于多智能体协作(Multi-Agent)深度研究系统,能够将宏大的模糊课题自动拆解,通过并行联网搜索、智能体内部审查与自纠错,最终撰写生成包含严谨数据、文献来源指向及可视化图表的深度研究长文。
DeepImageSearch
Firecrawl Swift SDK
Add a description, image, and links to the deepsearch topic page so that developers can more easily learn about it.
To associate your repository with the deepsearch topic, visit your repo's landing page and select "manage topics."