@DanKornas: Complex research agents get messy fast: planning, search, RAG, code execution, feedback, and final reports all need to …

X AI KOLs Timeline Tools
open-source research-agent multi-agent rag spring-ai docker plan-and-execute

Summary

DeepResearch is an open-source multi-agent research tool built with Spring AI Alibaba that converts queries into structured reports using dynamic planning, multi-agent roles, hybrid RAG, and Docker-based execution.

Complex research agents get messy fast: planning, search, RAG, code execution, feedback, and final reports all need to fit together. DeepResearch is an open-source Spring AI Alibaba research-agent app for builders exploring multi-agent research workflows. It helps you turn a research query into a structured report by combining dynamic planning, researcher/coder agents, multi-source search, Hybrid RAG, reflection, human feedback, and Docker-based Python execution. Key features: • Plan-and-execute workflow – breaks complex questions into planned steps before running them • Multi-agent roles – includes researcher and coder paths for investigation and analysis • Multi-source search – README lists Tavily, Jina, and Aliyun AI Search integrations • Hybrid RAG – combines vector and keyword retrieval for broader evidence gathering • Report export – supports HTML preview plus Markdown and PDF report formats It’s open-source (Apache-2.0 license). Link in the reply
Original Article
View Cached Full Text

Cached at: 06/10/26, 07:56 PM

Complex research agents get messy fast: planning, search, RAG, code execution, feedback, and final reports all need to fit together.

DeepResearch is an open-source Spring AI Alibaba research-agent app for builders exploring multi-agent research workflows.

It helps you turn a research query into a structured report by combining dynamic planning, researcher/coder agents, multi-source search, Hybrid RAG, reflection, human feedback, and Docker-based Python execution.

Key features: • Plan-and-execute workflow – breaks complex questions into planned steps before running them • Multi-agent roles – includes researcher and coder paths for investigation and analysis • Multi-source search – README lists Tavily, Jina, and Aliyun AI Search integrations • Hybrid RAG – combines vector and keyword retrieval for broader evidence gathering • Report export – supports HTML preview plus Markdown and PDF report formats

It’s open-source (Apache-2.0 license).

Link in the reply

GitHub: https://github.com/spring-ai-alibaba/deepresearch…

If you’re into AI, ML, agents, and building real systems, join my newsletter (it’s free): http://dankornas.substack.com

Most LLM features are easy to demo and much harder to operate.

AI Governance is useful because it maps the topic to engineering work you actually have to operate.

The book covers:

• Route model requests and control cost • Deploy and scale beyond a demo • Build more reliable generative AI applications • In AI Governance, you’ll learn how to: Match the right safeguards to your…

The production angle is the part I would pay attention to.

The demo is the easy part. The useful engineering work is making the system reliable once it touches real workflows.

Good fit for engineers building real AI systems and wanting a stronger mental model than another clean demo.

Link in the first comment.

Similar Articles

DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning

arXiv cs.AI

This technical report introduces DuMate-DeepResearch, a multi-agent framework for deep research tasks that decouples the agent core from a tool ecosystem, and incorporates graph-based dynamic planning, recursive two-level execution, and rubric-based test-time optimization. The system achieves state-of-the-art results on two deep research benchmarks, demonstrating the value of auditable agent infrastructure.

Mind DeepResearch Technical Report

Hugging Face Daily Papers

MindDR is a multi-agent deep research framework using a three-agent architecture (Planning, DeepSearch, Report) and a four-stage training pipeline, achieving competitive performance with ~30B-parameter models on multiple benchmarks. Developed by Li Auto and deployed as an online product, it also introduces MindDR Bench, a 500-query Chinese benchmark for evaluating deep research capabilities.

How we built our multi-agent research system

Anthropic Engineering

Anthropic details the architecture and engineering principles behind its new multi-agent research system, highlighting how parallel subagents using Claude Opus 4 and Sonnet 4 significantly outperform single-agent approaches in complex research tasks.