deer-flow
DeerFlow is an open-source super-agent framework for research, coding, and creation.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 74.7k
- Source
- skill-github
- Repository
- github.com/bytedance/deer-flow
Overview
DeerFlow is an open-source super-agent framework that handles tasks at different levels through sandboxing, memory, tools, skills, sub-agents, and message gateways. It enables AI to complete tasks ranging from minutes to hours. Deployment options include configuring and running via Docker or a local development environment. Ideal for developers and researchers requiring advanced task processing capabilities.
Capabilities
- ▪Supports multi-level task processing
- ▪Integrates sandboxing and memory functionality
- ▪Provides various tools and skills
- ▪Supports sub-agents and message gateways
Use cases
Setup
git clone https://github.com/bytedance/deer-flow.git; cd deer-flow; make setup
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How can I get started with DeerFlow quickly?
Clone the repository and run `make setup` to configure.
Which LLM providers does DeerFlow support?
Supports Claude Code, Codex, Cursor, Windsurf, and others.
Related skills
mantis
Provides security review capabilities for AI coding agents, automatically discovering, reproducing, and fixing vulnerabilities.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.