#18 · Primary category: AI Agents & Automation

deer-flow

agent agentic agentic-framework agentic-workflow ai ai-agents deep-research harness langchain langgraph langmanus llm multi-agent nodejs podcast python superagent typescript

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.

Project last updated:08/29/26

GitHub Stars

81.1K

Forks

11.2K

Contributors

382

License

MIT

Why we included this project

DeerFlow is a full agent harness rather than a single-purpose tool, so it fits teams that need one system to carry long, multi-step jobs from research through coding to a finished artifact. It coordinates sub-agents, persistent memory, and isolated sandboxes, letting a single session browse the web, write and run code, manage files, and delegate subtasks without you babysitting each step. The 2.0 rewrite, built on LangGraph, ships with an interactive setup wizard, Docker deployment, and a terminal workbench, so it's practical to stand up for real workloads, not just a demo. That combination makes it a strong starting point for teams that want to move from prototype to production without assembling many separate pieces.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category