LessAI ToolsAI plugin directory
← Back to plugins

Task skills

DeerFlow

bytedance/deer-flow

Run multi-step research and creation with an AI workspace that includes reusable skills.

Get started ↓

What is DeerFlow?

Prepared by LessAI Tools from public project documentation

DeerFlow is a complete AI agent framework with reusable skills, rather than a small skill-only download. It coordinates assistants, memory and isolated workspaces for research, coding and content tasks. Its public skill library includes deep research and data analysis; use it when you need a workflow environment as well as task instructions.

DeerFlow setup documentation

What you need

  • For local development, follow the official setup for Python 3.12+, Node.js 22+, pnpm, uv and nginx.
  • Configure the model provider and required credentials. Container sandbox options need the corresponding container setup.

Limitations and costs

  • Deploying the framework takes more setup than installing a single skill; connected models and tools may charge fees.
  • The project recommends a trusted local network. External access needs authentication and network restrictions.
  • DeerFlow 2 is a rewrite and differs from the older research framework. This site has not deployment-tested it.
Setup and usage guide ↗

Based on public documentation; not individually installed and tested here.

DeerFlow use cases

  • Multi-step research with delegated assistant tasks
  • Public skills for research, analysis and creation
  • A workspace with memory and sandbox options

Official project & documentation

View source code ↗Project website ↗Setup and usage guide ↗

The project’s original description

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

Alternatives to DeerFlow for similar tasks

Matches the main use case first, then shared tasks and stars. Setup methods may differ.

  • Last30Days — Research recent discussions across social and web sources, then collect a source-linked brief.
  • Jev SEO — Audit a site from its homepage and export prioritized PDF, spreadsheet, and Markdown reports.
  • Vercel Skills CLI · Find Skills — Find a skill for your task, then choose which coding assistant and project should use it.

Sources and ranking

This directory lists AI development plugins with public source code and a clear purpose. Browse by task, then open an introduction to learn what a project does, who it is for, and what you need to get started. It covers selected projects, not every AI plugin.

How do the three plugin types differ?

Tool connections (MCP) let AI assistants use external tools such as browsers, code repositories and databases. MCP is the protocol used for these connections.

Reusable skills give a compatible AI assistant instructions and guidance for a particular task.

Editor plugins run inside the software you use to write code, adding AI chat, completions or suggested edits.

How does “Most starred” work?

Projects are sorted by their total GitHub stars. Stars indicate interest; they are not downloads, active users or quality scores. A skill pack counts as one project. Daily star growth is not shown without historical records.

What does “Recently updated” mean?

It uses the most recent code push, which may not be a new release. The 7-day filter checks that project update time; ranking still uses all-time stars. Each introduction shows when its star count was collected. Failed updates keep the last saved data.

Introductions are based on public project documentation. These projects have not each been installed and tested here. Check the project documentation for setup, compatibility and service costs. Refreshing this list only reads saved data; it does not start collection.

UTC+8

Pass a useful find along

Pick a draft and a platform. You can edit before posting.