deer-flow

DeerFlow is ByteDance's open source answer to Manus and ChatGPT's agent mode: an agent harness built to work a task for minutes or hours, not just answer a prompt. It ships the whole stack (backend, web UI, sandboxed execution, chat gateways for Slack, Telegram, Discord, and more) and gives the agent a real filesystem, persistent memory, loadable skills, and sub-agents to delegate to. MIT licensed, completely free.

Self-hosting is real work. Python, Node, and nginx, an interactive setup wizard, Docker as the recommended path, and a hardware floor around 4 vCPU and 8 GB of RAM just to evaluate it. It's model-agnostic through any OpenAI-compatible API. The README is refreshingly blunt that improper deployment introduces security risks: this thing runs code, so it's designed to stay bound to localhost unless you put auth and network isolation in front of it.

Use it if you want long-horizon agents on your own infrastructure with your choice of models. Solo and small teams: free, plus tokens. If you just want agent orchestration as a library, LangGraph (which DeerFlow builds on) or CrewAI is the lighter path, and OpenHands is the closest open comparison.

The catch: 2.0 is a ground-up rewrite that shares no code with v1, so the project is popular but the current codebase is young, with a long open-issue tail. And an agent with shell access is a loaded tool. Mount credentials into its sandboxes carelessly and you'll regret it.