automation

deer-flow: Automate Tasks

Name: deer-flow: Automate Tasks
Author: bytedance

Founders automate tasks with deer-flow, a Python SuperAgent harness. Simplify workflows with this open-source tool.

79,709 stars10,902 forksPythonHealth Score 8/10Updated 8/11/2026100% free · open source

What it does

Deer-flow automates tasks by harnessing the power of Python SuperAgent, simplifying workflows for founders and developers.

Install / run

pip install deer-flow

When to use it

•When automating complex workflows with multiple dependencies
•As a replacement for manual, repetitive tasks in development and testing
•To streamline data processing and integration across different systems

Quick start

1Create a new workflow by running `deer-flow init` to generate a basic configuration
2Define tasks and dependencies in the `deer.yaml` file, specifying the `name`, `type`, and `params` for each task
3Use the `deer-flow run` command to execute the workflow, optionally specifying the `--config` flag to override default settings
4Monitor and manage workflow execution using the `deer-flow logs` and `deer-flow status` commands
5Customize the workflow by adding Python code to the `tasks` directory, leveraging the full power of the SuperAgent harness

Ready-to-paste prompt

deer-flow run --config deer.yaml --task my_task --param foo=bar

Heads up: Ensure Python 3.7 or later is installed, as deer-flow relies on modern Python features and may not be compatible with earlier versions

Saves to your device

Topics

agent

agentic

agentic-framework

agentic-workflow

ai-agents

deep-research

harness

langchain

langgraph

langmanus

llm

multi-agent

nodejs

podcast

python

superagent

typescript

How deer-flow: Automate Tasks works

Codeflow

Free to inspect

Deer-flow: Automate Tasks is a very large Python project (~226k lines across 1090 code files, plus 733 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit this month, MIT license, has a test suite.

Size

Very large codebase

~226k lines · 1090 code files · days to read — use, don't read

Setup

One-command install

Installs like a normal app — add your API keys. Reading the code is optional.

Runs on

Docker

Needs API keys (.env)

Python 82%TypeScript 14%MDX 2%HTML 1%Shell 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
.env.example
The API keys and settings you must provide
4
skills/public/academic-paper-review/SKILL.md
Inside skills/ — an example of what the AI is told to do
5
examples/deerflow-extension-example/README.md
A worked example — copy this to get going