AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Multi-Agent/
deer-flow
deer-flow logo

deer-flow

Active·★ 84.5k·MIT·Updated 2026-10-27
★ Most Popular★ Essential★ Trending

DeerFlow is ByteDance's open-source "super agent harness": a runtime that gives an AI agent a filesystem, sandboxed code execution, long-term memory, skills and sub-agents so it can carry out tasks that take minutes to hours. Version 2.0 is a ground-up rewrite built on LangGraph and LangChain; the original Deep Research framework is still maintained on the 1.x branch.

It suits developers and teams who want a ready-made agent runtime rather than wiring one together from libraries. Typical tasks include in-depth research reports, building data pipelines, generating slide decks and dashboards, and automating content workflows. Tasks can be sent from the web workspace or from messaging apps such as Telegram, Slack, Feishu/Lark, WeChat, WeCom, DingTalk and QQ, and it can retrieve from private knowledge bases through RAGFlow.

Getting started: Docker is the recommended path (Docker Compose v2.24+), with `make docker-init` and `make docker-start` after configuring models. For local evaluation plan for at least 4 vCPU, 8 GB RAM and 20 GB of free disk; a long-running shared server should start at 8 vCPU and 16 GB RAM. Linux with Docker is the recommended target for persistent deployments.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-24.

License
MIT
Latest release
v2.1.0 · 2026-09-24
Last commit
2026-10-24
Contributors
609
Forks
11,804
Open issues and PRs
983
First published
2025-05-07

Source: GitHub, npm and PyPI public APIs.

#LLM#Multi-Agent#Research Automation#Web Search#RAG#Web Browsing#Coding
$ Install
$ uv sync
↗ Visit site★ GitHub
01

Features

01Multi-model LLM integration via LiteLLM with OpenAI-compatible API
02Comprehensive web search and crawling using diverse engines like InfoQuest and Tavily
03RAG integration with multiple vector databases including Qdrant and RAGFlow
04Human-in-the-loop collaboration with intelligent clarification and interactive plan modification
05Automated content creation for podcasts and presentations with AI-powered script generation
02

Why choose it

+Batteries included: sandbox, filesystem, memory, skills, sub-agents and scheduled tasks come out of the box instead of being assembled by hand.
+Handles long-running, multi-step tasks, with context compaction and sub-agent delegation designed for them.
+Reachable from many messaging apps (including Feishu, WeChat, WeCom and DingTalk) without needing a public IP.
+MIT licensed, with tracing integrations (LangSmith, Langfuse) and support for multiple model providers.
03

Trade-offs

!Resource-hungry: 2 vCPU / 4 GB is usually not enough, and shared servers need 8 vCPU / 16 GB or more.
!It has high-privilege capabilities (system commands, file operations) and is designed for a trusted local environment; the project explicitly warns against exposing it to the internet without proper access control.
!Version 2.0 shares no code with 1.x, so tutorials and integrations written for the original Deep Research framework may not apply.
!A large, fast-moving codebase with many configuration options; expect time spent on setup and tuning.
05

Maintenance check

ActiveChecked: 2026-10-23
Last commit
2026-10-23
Commits, last 90 days
100+
Releases, last 90 days
1
Latest release
v2.1.0 (2026-09-24)
Open issues
970
Recent issues with at least one comment
1/11
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 32, 42, 27, 61, 80, 91, 134, 187, 190, 259, 176, 201

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #1156 有没有人建个QQ群互相讨论的？没有的话我临时创建一个，Q群号：71172934740 comments · 2026-03-16
  • #1669 RoadMap of DeerFlow Q230 comments · 2026-03-31

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You want a batteries-included LangGraph agent runtime with a file system, isolated bash/Docker sandbox, persistent memory, and sub-agent delegation.
  • You want to trigger long-running tasks from Feishu, WeCom, DingTalk, WeChat, Slack, or Telegram without exposing a public IP.
Look elsewhere if
  • Your machine or VPS has only 2 vCPU / 4 GB RAM; DeerFlow recommends 8 vCPU / 16 GB RAM for shared servers.
  • You only want a lightweight script that writes cited web research reports without running local sandboxes; GPT Researcher is much lighter.
06

How it differs

GPT Researcher logovs GPT Researcher★ 30.3k

DeerFlow 2.0 is a full agent runtime with code sandboxes, skills, scheduled tasks, and IM bot channels; GPT Researcher is a focused research-report generator.

Full comparison →
OpenClaw logovs OpenClaw★ 393.2k

Both run locally and connect to messaging apps. DeerFlow is built on LangGraph in Python with a strong focus on deep research and sandboxed sub-agent tasks; OpenClaw is a Node.js personal AI assistant with 20+ messaging channels and native desktop/mobile companion apps.

Full comparison →
07

Compatibility

LiteLLM
Native Integration
Verified via docs
OpenAI-compatible APIs
API Support
Verified via docs
InfoQuest
Recommended Search
Verified via docs
Tavily
Default Search
Verified via docs
Jina
Default Crawler
Verified via docs
RAGFlow
RAG Provider
Verified via docs
08

Quick start

1
$ uv sync
09

Use cases

↳Conducting deep research and generating comprehensive reports with multimedia content
↳Automated creation of podcasts, articles, and presentations from research findings
↳Intelligent information retrieval and analysis for complex queries and trending topics
10

Alternatives

⚡Top VS:
VSGPT Researcher★30.3k→VSOpenClaw★393.2k→VSPydantic AI★20.9k→VScodefuse-chatbot★1.3k→
GPT Researcher logo
GPT Researcher★ 30.3k
An autonomous agent that conducts deep research on any data using any LLM provider, producing detailed reports with citations from web and local sources.
VSCompare→
OpenClaw logo
OpenClaw★ 393.2k
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
VSCompare→
Pydantic AI logo
Pydantic AI★ 20.9k
GenAI Agent Framework, the Pydantic way. A Python agent framework designed for production with type safety at its core.
VSCompare→
codefuse-chatbot logo
codefuse-chatbot★ 1.3k
An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.
VSCompare→
LazyLLM logo
LazyLLM★ 3.9k
Easiest and laziest way for building multi-agent LLMs applications.
VSCompare→
MiroFlow logo
MiroFlow★ 3.1k
MiroFlow is an agent framework that enables tool-use agent tasks, featuring a reproducible GAIA score of 82.4%.
VSCompare→
edsl logo
edsl★ 510
Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.
VSCompare→
mcp-agent logo
mcp-agent★ 8.6k
Build effective agents using Model Context Protocol and simple workflow patterns
VSCompare→
See all alternatives →

Featured in these lists

  • Open-Source Multi-Agent Frameworks: CrewAI, Pydantic AI, Google ADK, Microsoft Agent Framework & More
  • Open-Source RAG Platforms & Deep Research Agents: RAGFlow, MaxKB, GPT Researcher, DeerFlow & More

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs07Compatibility08Quick start09Use cases10Alternatives
bytedance /
deer-flow
↗

ByteDance's open-source super-agent runtime for long tasks

84.5k12kMIT
Last commit1d ago
StatusActive
CategoryMulti-Agent
Contributors609
Latest releasev2.1.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.