---
name: "Run long-horizon research and coding agent workflows with DeerFlow"
slug: "run-long-horizon-research-and-coding-agent-workflows-with-deerflow"
description: "Use DeerFlow to orchestrate subagents, memory, sandboxes, tools, and skills for supervised research, coding, and creation tasks that take minutes to hours."
github_stars: 67524
verification: "security_reviewed"
source: "https://github.com/bytedance/deer-flow"
author: "ByteDance"
publisher_type: "vendor"
category: "Code Quality & Review"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "bytedance/deer-flow"
  github_stars: 67524
---

# Run long-horizon research and coding agent workflows with DeerFlow

Use DeerFlow to orchestrate subagents, memory, sandboxes, tools, and skills for supervised research, coding, and creation tasks that take minutes to hours.

## Prerequisites

DeerFlow application, supported LLM provider credentials, configured tools, memory, sandboxes, and optional skills/subagents

## Installation

Requirements and caveats from upstream:
- [![Python](https://img.shields.io/badge/Python-3.12%2B-3776AB?logo=python&logoColor=white)](./backend/pyproject.toml)
- [![Node.js](https://img.shields.io/badge/Node.js-22%2B-339933?logo=node.js&logoColor=white)](./Makefile)

Basic usage or getting-started notes:
- We strongly recommend using Doubao-Seed-2.0-Code, DeepSeek v3.2 and Kimi 2.5 to run DeerFlow

- Source: https://github.com/bytedance/deer-flow
- Extracted from upstream docs: https://raw.githubusercontent.com/bytedance/deer-flow/HEAD/README.md

## Documentation

- https://deerflow.tech

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/run-long-horizon-research-and-coding-agent-workflows-with-deerflow/)