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 ga
What is 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.
Overview of deer-flow
What it is
DeerFlow (Deep Exploration and Efficient Research Flow) is an open-source super agent harness that orchestrates sub-agents, memory, and sandboxes to perform a wide range of tasks. It is powered by extensible skills and designed to handle long-horizon tasks that may take minutes to hours.
Key features
- Orchestrates sub-agents for parallel or sequential task execution - Integrates memory (long-term memory, chat archive, session goals)
- Provides sandboxed execution environments and file system access - Supports extensible skills and tools, including custom skill exports - Offers private knowledge retrieval via RAGFlow integration - Enables agentic browser control for web-based tasks - Includes context engineering, manual context compaction, and current task notes
Use cases
DeerFlow is suitable for long-horizon research, coding, content creation, and complex task automation that require coordinated sub-agents, memory, and sandboxed execution.
Getting started
Clone the repository and run the setup wizard: bash git clone https://github.com/bytedance/deer-flow.git cd deer-flow make setup The wizard guides you through choosing an LLM provider, optional web search, and execution/safety preferences.
License and pricing
DeerFlow is released under the MIT license and is open source.
Based on the project's public README and repository metadata.
