OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

DeerFlow

DeerFlow is an open-source SuperAgent harness for building and running long-horizon agents that research, code and create through coordinated tools, sandboxes, memories, skills and subagents.

Independent OpenViST project profile, based on linked sources.

DeerFlow — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use DeerFlow when a project needs an extensible agent harness for tasks spanning multiple stages and potentially lasting minutes to hours, rather than a narrowly scoped single interaction.

Who it is for

  • Developers building self-hosted AI agent applications
  • Teams automating multi-step research workflows
  • Engineers creating coding agents that need sandbox and file-system access
  • Builders assembling content workflows from research, tools and delegated subagents

Documented uses

  • Coordinate long-running research tasks
  • Delegate work to specialized subagents
  • Execute longer coding tasks in a sandbox
  • Combine memory, tools and skills in content-creation workflows
  • Connect an agent service through a message gateway
Before you choose

Requirements & limits

The repository is public, open source and MIT-licensed. It documents Docker and local-development paths and identifies Linux, macOS, Windows, CLI and server-oriented use in its technical profile.

  • Python 3.12+ and Node.js 22+ are identified as runtime or development requirements.
  • Docker is the repository’s recommended deployment option when available; local development is also documented.
  • The framework includes sandboxes, memory, tools, skills and subagents, making it suited to composed workflows rather than a single fixed agent behavior.
  • Self-hosting places deployment responsibility on the operator, and the repository includes a security notice for deployment.
  • The repository recommends particular model families for running DeerFlow, while model-provider selection is also documented.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
DeerFlowCoordinate long-running research tasksCLI, Docker, Linux, macOSThe repository is public, open source and MIT-licensed. It documents Docker and local-development paths and identifies Linux, macOS, Windows, CLI and server-oriented use in its technical profile.
AgeniteDefine typed tools with JSON Schema validation and error handling.CLI
VeldraCreate an agent with a policy, tools, skills, knowledge base and reasoning method.Self-hostedThe documented deployment is self-hosted and uses a sign-in gate after a first-run administrator account is created.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
bytedance/deer-flow · Official homepage title · retained in its source language
How we review sourcesSuggest a correction