@DanKornas: Research agents need more than a prompt—they need search, extraction, planning, source tracking, and synthesis. Open De…
Summary
Open Deep Research is an open-source Next.js app that combines Firecrawl Search and Extract with a reasoning model to perform iterative web research loops, including search, extraction, planning, source tracking, and synthesis.
View Cached Full Text
Cached at: 07/22/26, 12:28 PM
Research agents need more than a prompt—they need search, extraction, planning, source tracking, and synthesis.
Open Deep Research is an open-source Next.js app for builders studying or adapting agentic web-research workflows.
It helps you inspect a complete research loop by combining Firecrawl Search and Extract with a reasoning model that analyzes findings, identifies gaps, runs follow-up searches, and synthesizes a final response.
Key features: • Iterative research loop – searches the web, extracts top pages, analyzes gaps, and plans follow-up queries. • Live research trace – streams progress, activities, and source links to the interface. • Model flexibility – documents OpenAI, OpenRouter, and AI SDK provider switching. • Persistent workspace – saves chat history and user data in Postgres, with Vercel Blob for files. • Deployment options – includes local setup instructions, Docker files, and one-click Vercel deployment.
It’s open-source (Apache License 2.0).
Link in the reply
Similar Articles
@DanKornas: Complex research agents get messy fast: planning, search, RAG, code execution, feedback, and final reports all need to …
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.
@DanKornas: DeepDive is a pattern for deep search agents: synthesize QA from knowledge graphs, then train multi-turn browsing with …
DeepDive is a pattern for building deep search agents that synthesizes QA from knowledge graphs and trains multi-turn browsing with reinforcement learning (GRPO). It includes entity obfuscation and test-time scaling with tool calls.
@DanKornas: Building a research agent is one problem. Connecting its search loop, backend, and usable frontend is another. Gemini F…
An open-source full-stack research agent example using Gemini, LangGraph, React, and Google Search, demonstrating an end-to-end workflow with dynamic query generation, reflection loops, and cited answers.
@DanKornas: Keeping up with agentic deep research means tracking products, implementations, papers, and benchmarks across scattered…
Awesome-Deep-Research is a curated GitHub resource index that organizes products, implementations, papers, and benchmarks for agentic deep research, helping researchers and builders scan the field faster.
langchain-ai/open_deep_research
Open Deep Research is a configurable, fully open source deep research agent by LangChain that supports multiple model providers, search tools, and MCP servers, achieving competitive performance on the Deep Research Bench leaderboard.