DeerFlow

ByteDance's long-horizon research **harness**: a LangGraph-based agent loop that researches, codes, and creates using sandboxes, memory, tools, and subagents behind a message gateway—an alternative to the reference gpt-researcher stack for multi-hour tasks.

memorymulti-agentsandboxpython

Stars: 84.8k
Adoption surface: complex
Autonomy: headless
Recovery: resumable
License: ✅ open-source
Category: Research and task-specific harnesses

Repository ↗ Example: Project README ↗

Related in Research and task-specific harnesses

gpt-researcher
AutoResearchClaw
MiroThinker
openagents
Jev Social

Maintain DeerFlow? Add the badge

Paste this into your README so readers can find the list and see how DeerFlow compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)