Chinese AI Tools
ZH

ByteDance / Volcano Engine

DeerFlow

DeerFlow 2.0, also described as Deep Exploration and Efficient Research Flow, is an open-source SuperAgent harness from ByteDance. The GitHub repository positions it as a runtime that researches, codes and creates with sandboxes, memories, tools, skills, sub-agents and a message gateway, handling tasks that can run from minutes to hours. The official website presents DeerFlow as an open-source SuperAgent for deep research, long task running, multi-model support and Docker-based sandbox execution. The project is built on LangGraph and LangChain, includes a frontend and backend, supports MCP servers, agent skills, sub-agent decomposition, file-system workspaces, long-term memory, IM channels such as Slack, Telegram, Feishu/Lark, WeChat, WeCom and DingTalk, and lists models including Doubao-Seed-2.0-Code, DeepSeek v3.2 and Kimi 2.5. It is MIT licensed and self-hosted, with a security warning that public or multi-user deployment needs authentication, network isolation and strict access controls.

Globally availableFull English UILimited APIFreeTrusted

Quick answers

At a glance

Overview
ByteDance's open-source long-horizon SuperAgent harness for deep research, coding, content creation, skills, sub-agents, memory and sandboxed execution.
Best fit
Teams that want to self-host a Chinese-origin open-source agent harness for deep research, report generation, coding, file-based workflows and long-running multi-agent tasks.
Trust
4/4 sources verified, recently checked · 2026-05-17
Coverage
100/100

Editorial verdict

Best for

Teams that want to self-host a Chinese-origin open-source agent harness for deep research, report generation, coding, file-based workflows and long-running multi-agent tasks.

Avoid if

Avoid exposing it on public networks before hardening authentication, sandboxing, file access, shell access, network policy and audit logging.

Why it matters

DeerFlow belongs in Productivity because it is a SuperAgent harness broader than an AI coding agent: its core promise is long-horizon research, creation and workflow execution through skills, sub-agents and sandboxes.

Pricing

MIT open-source self-hosted project; model, search and infrastructure costs depend on configured providers

Payment

Self-hosted open source, Configured model provider billing, BytePlus / Volcano Engine Coding Plan, Optional search provider billing

Commercial use

Commercial use should follow the current product, API, model license and billing terms.

Privacy

Review prompt, file, media upload, retention and training-use terms before sensitive workloads.

Use-case fit

Deep research and report generation

Strong

Use DeerFlow for multi-step research tasks that collect information, analyze sources and produce reports or webpages.

Long-running agent workflows

Strong

Sub-agents, memory, skills and filesystem workspaces make it relevant for tasks that take minutes to hours.

Self-hosted agent runtime

Strong

Docker, local development, production deployment scripts and an embedded Python client make it usable as an internal agent platform.

Messaging-app agent channels

Medium

Slack, Telegram, Feishu/Lark, WeChat, WeCom and DingTalk channels make it relevant for team-facing assistant workflows.

Global user checklist

RegistrationConfirmedThe GitHub repository and official website are public, with Docker and local setup paths.
English UIConfirmedThe README, official site and docs are English-facing, with additional localized READMEs.
API and docsPartialDeerFlow exposes Gateway/LangGraph-style APIs, embedded Python client and MCP configuration, but it is not a hosted model API.
Commercial usePartialThe project is MIT licensed; commercial use still depends on configured models, search providers, skills and data sources.
Data and privacy termsReviewAgents can read/write files, run tools and use shell access; data handling and execution policy must be reviewed before team deployment.
Coverage · 100/100

Model names, quotas, release status, regional access and commercial terms can change quickly; recheck official sources before procurement or production use.

Pros

  • - Open-source MIT SuperAgent harness with strong GitHub adoption
  • - Includes skills, tools, sub-agents, memory, filesystem workspace and sandbox-aware execution
  • - Supports Docker deployment, MCP servers, IM channels and multiple model providers

Cons

  • - It is an agent runtime to deploy and operate, not a hosted no-code SaaS
  • - High-privilege tool execution creates serious security risk if exposed without authentication and network controls
  • - Teams still need to configure model providers, search tools, sandbox mode and runtime resources

Decision paths

kimi

deepseek-agent-integrations

qoder

atomcode

Sources

DeerFlow GitHub repository

official · en · verified 2026-05-18

Confirms ByteDance repository, DeerFlow 2.0 positioning, MIT license, setup flow, model routing notes, features, IM channels and security warning.

DeerFlow official website

official · en · verified 2026-05-18

Confirms official product messaging, case studies, Agent Skills, Docker sandbox, long task running, memory and multi-model support.

DeerFlow installation guide

docs · en · verified 2026-05-18

Linked setup instructions for local development and agent-assisted bootstrap.

BytePlus InfoQuest docs

docs · en · verified 2026-05-18

Repository links InfoQuest as an integrated BytePlus search and crawling toolset.

Reviews