DeerFlow

Rating:

Rate it!

Category:AI Agent Development Frameworks

Overview

Open-source super agent harness by ByteDance for long-horizon research, coding, and creation with sub-agents, memory, sandboxes, and skills.

Visit website

Best For Professions:

software developer ai engineer machine learning engineer researcher automation engineer technical founder product engineer

DeerFlow, from ByteDance, is an open-source long-horizon super agent harness for tasks such as research, coding, and content creation. The GitHub repository describes DeerFlow as orchestrating sub-agents, memory, sandboxes, tools, skills, and a message gateway to handle tasks that can take minutes to hours. DeerFlow 2.0 is a ground-up rewrite of the original Deep Research framework, with the earlier framework maintained on the 1.x branch. The project is distributed on GitHub under the MIT license.

Autonomy level

80%

Reasoning: DeerFlow is described in its official repository as an open-source long-horizon super agent harness that orchestrates sub-agents, memory, and sandboxes, which directly indicates a design focused on multi-step, goal-driven autonomy rather than single-turn assistance. Its architecture coordinates multiple specialized sub-agents, allowing the system t...