D

deer-flow

Free

An open-source long-horizon SuperAgent harness that researches, codes, and creates.

Visit Website

At a glance

Explore the listed capabilities, then check the details that matter to you.

  • Open source SuperAgent harness
  • Long horizon task execution
  • Research and coding tasks
Related by shared tags and keywordsClawbot-1nanobrowsersim
agentagenticagentic-frameworkagentic-workflowaiai assistantautomation
deer-flow screenshot 1

Overview

DeerFlow is an open-source super agent harness that orchestrates sub-agents, memory, and sandboxes, powered by extensible skills. Version 2.0 is a ground-up rewrite that shares no code with v1; the original Deep Research framework is maintained on the 1.x branch. The project provides an official website with demos and allowlisted, read-only case studies that do not require sign-in.

Setup begins by cloning the repository and running make setup, which launches an interactive wizard for choosing an LLM provider, optional web search, and execution/safety preferences such as sandbox mode, bash access, and file-write tools. The wizard generates a minimal config.yaml and writes keys to .env. Users can run make doctor to verify setup and get actionable fix hints. Operators can extend lead-agent, subagent, and DeerMem extraction prompts with literal prepend/append configuration without editing source templates. Optional per-model request_admission paces requests to help stay within provider request-per-minute limits. Administrators can open Settings → Models to add, edit, test, and enable/disable shared OpenAI-compatible Chat Completions models without editing config.yaml.

DeerFlow has integrated the InfoQuest intelligent search and crawling toolset from BytePlus. Official DeepSeek models at https://api.deepseek.com or https://api.deepseek.com/v1 automatically use DeerFlow's DeepSeek adapter, preserving reasoning content across tool calls and honoring output token limits. YAML models remain read-only in this page and take precedence on name conflicts, while managed models are shared by the deployment. The encrypted catalog and a generated local encryption key are stored in $DEER_FLOW_HOME/managed-models/.

Pricing

Free

Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.

Visit Website

Prices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.

Use Cases

  • Teams use DeerFlow to orchestrate sub-agents, memory, and sandboxes for research and automation.
  • Developers use a one-line prompt to have coding agents clone and bootstrap DeerFlow for local development.
  • Operators use prompt overlays to extend lead-agent, subagent, and DeerMem extraction prompts without editing source templates.
  • Administrators use Settings → Models to manage shared OpenAI-compatible Chat Completions models without editing config.yaml.
  • Teams use InfoQuest for intelligent search and crawling with a free online experience.
  • Developers use make doctor to verify setup and get actionable fix hints.
  • Teams use per-model request_admission to pace requests within provider request-per-minute limits.
  • Developers use DeerFlow's DeepSeek adapter for official DeepSeek models to preserve reasoning content across tool calls.

Features

Open source SuperAgent harness

Long horizon task execution

Research and coding tasks

Content creation tasks

Sandbox and memory support

Tool and skill usage

Subagent task coordination

Message gateway support

Reviews

No reviews yet. Be the first to share your experience!

See the best deer-flow alternatives

Rankings & collections