D
deer-flow
bytedance/deer-flow
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
★79.5kstars
Python
MIT
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?A , built with Python open-source project in the Agents category, core strengths: agent/agentic
Who made it?Maintained by bytedance team, 79.5K⭐ on GitHub, #15 out of 2166 in Agents
Why does it exist?As the Agents landscape evolved, the bytedance team identified the need for better agent solutions. deer-flow was created to simplify agentic workflows.
What can it do?Key use cases: agentic-framework, agentic-workflow, ai-agents
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/bytedance/deer-flow | 官网 https://deerflow.tech
🔗 github.com/bytedance/deer-flow | 官网 https://deerflow.tech
Topics
agentagenticagentic-frameworkagentic-workflowaiai-agentsdeep-researchharnesslangchainlanggraphlangmanusllmmulti-agentnodejspodcastpythonsuperagenttypescript