explaingit

bytedance/deer-flow

🔥 Hot★ 68,485PythonAudience · developerComplexity · 4/5ActiveLicenseSetup · moderate

TLDR

An AI agent framework that orchestrates long-running automation tasks, research, coding, planning, across multiple tools, sub-agents, and memory, deployable via Docker or locally.

Mindmap

mindmap
  root((DeerFlow))
    What it does
      Multi-step automation
      Agent orchestration
      Long-term memory
      Tool integration
    Key features
      Sub-agent delegation
      Code sandbox
      Web search tools
      YAML configuration
    Use cases
      Technical reports
      Codebase generation
      Research aggregation
      Extended workflows
    Tech stack
      Python 3.12
      Node.js 22
      Docker
    Deployment
      Local development
      Docker containers
      Web interface

Things people build with this

USE CASE 1

Build an AI agent that researches a topic and writes a complete technical report over several hours.

USE CASE 2

Create a system that autonomously writes and tests code across multiple files in a sandbox environment.

USE CASE 3

Set up a multi-agent workflow where specialized sub-agents handle different parts of a complex task in parallel.

USE CASE 4

Deploy a long-running automation that aggregates information from web searches and external APIs into structured outputs.

Tech stack

Python 3.12Node.js 22DockerYAML

Getting it running

Difficulty · moderate Time to first run · 30min

Requires Docker or Python 3.12 + Node.js 22 installed; likely needs API keys for external tools/LLMs.

Use freely for any purpose including commercial, as long as you keep the copyright notice.

In plain English

DeerFlow is an open-source AI agent framework built by ByteDance that lets you create powerful, long-running automation systems capable of researching topics, writing code, and producing outputs over extended periods, tasks that might take minutes or even hours to complete. The problem it solves is that standard AI chatbot interactions are short and stateless; DeerFlow enables AI agents that can plan, remember context, delegate to sub-agents, and use external tools in a coordinated way. At its core, DeerFlow acts as a harness that orchestrates multiple components together: skills and tools the agent can call (such as web search or code execution), sub-agents that handle parallel or specialized work, a sandbox environment for safely running code, and long-term memory so the agent can retain information across steps. Users configure which AI model to use, the README mentions support for models like GPT-4o, DeepSeek, Gemini, and others via a YAML configuration file, then run the system either through Docker or a local development setup. The frontend is a Node.js web interface while the backend logic runs in Python. DeerFlow is version 2.0, described as a complete rewrite from its earlier deep-research-focused v1. You would use this if you need an AI that can autonomously complete multi-step research or coding tasks, for example writing a full technical report, building a small codebase, or aggregating information from many sources. The tech stack is Python 3.12 on the backend with Node.js 22 on the frontend, deployable via Docker.

Copy-paste prompts

Prompt 1
How do I set up DeerFlow to create an AI agent that can research a topic and write a full technical report? Walk me through the YAML config and Docker setup.
Prompt 2
Show me how to add custom tools and skills to a DeerFlow agent so it can call my own APIs and execute specialized functions.
Prompt 3
How do I configure sub-agents in DeerFlow so they can work in parallel on different parts of a task?
Prompt 4
What's the best way to set up long-term memory in DeerFlow so my agent remembers context across multiple hours of work?
Prompt 5
How do I deploy a DeerFlow agent to production using Docker, and what models (GPT-4o, DeepSeek, Gemini) work best?
Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.