← Discover
Discover · GitHub · Deer Flow↑ +442 today

AI agent for complex tasks

Developed by ByteDance, Deer-Flow is an open-source superagent framework designed to perform long-running tasks. System; It can autonomously research and code complex workflows using a sandbox, memory management and sub-agents.

Updates

  • August 2, 2026: Stars 72,905 → 78,818, latest release v2.0.0 (June 25, 2026).

What you get

  • Autonomous research and coding ability
  • Working in a safe sandbox environment
  • Long-term memory and subagent management

Installation

Cloning the repository
git clone https://github.com/bytedance/deer-flow.git
   cd deer-flow
Starting the setup wizard
make setup

Running it

Launching with Docker
make docker-init    # Pull sandbox image (only once or when image updates)
make docker-start   # Start services (auto-detects sandbox mode from config.yaml)

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

Clone the DeerFlow repository to my computer and then run the make setup command to complete the necessary configuration for the local development environment. Help me configure options such as LLM provider, web search preferences, and security settings during the setup wizard.

Related dictionary terms

SuperAgentSandboxLLMArtificial Intelligence
Who it is forIt is suitable for developers and developers who want to manage and code complex workflows autonomously.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-22: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.