JiuwenSwarm_Introduction.mp4
JiuwenSwarm is an Agent system that makes multi-agent collaboration truly work. Designed for developers and teams who need to automate complex tasks, it helps users drive multi-agent collaboration, Skill self-evolution, and tool invocation through natural language — delivering end-to-end from intent to result. It runs on a single machine or across a cluster, and you can reach it from a browser, a terminal, or the chat apps you already use.
Why JiuwenSwarm
| Capability | Value |
|---|
| Multi-Agent Collaboration | The Leader decomposes a complex task and assembles teams, multi agents specialize and negotiate dynamically. |
| Distributed Agent Swarm | Leader and Teammates deploy across processes and machines, coordinating at scale. |
| Swarmflow | Deterministic multi-stage workflows via Python scripts: the Leader hands off between stage agents; supports HITL (human / human_session), team token budget, TUI /swarmflows run-tree monitoring, opt-in progressive tool exposure for workers (swarmflow_progressive_tool), and AgentGroup expert workers (agent_template). |
| Skill Self-Evolution | Automatically detects error signals and user dissatisfaction, then optimizes Skill definitions |
| Skill Hub Sharing | Capability assets are built once and reused everywhere, search, install, remix, and publish Skills through the Swarm Skills Hub |
| Auto Harness | Evaluation drive end-to-end optimization of the Harness itself, which learns and improves in practice with no model-weight training |
| AI Infrastructure Compatibility | Compatible with Huawei Cloud MaaS and other mainstream platforms, OpenAI-compatible APIs, and local models |
| Tool Permissions & Security | Every step is under your control, tools require approval before execution, file access goes through a whitelist, and sensitive operations are intercepted |
Install
Desktop
One-click install, no environment setup — the quickest way to try JiuwenSwarm.
Download and follow the installer prompts to get started.
On Linux, install via Command Line or from source below.
Command Line
Requires Python >=3.11,<3.15.
# Install JiuwenSwarm
pip install workswarm
# Use China mirror (recommended)
pip install workswarm -i https://pypi.tuna.tsinghua.edu.cn/simple
# Initialize JiuwenSwarm (first-time setup)
jiuwenswarm-init
# Start JiuwenSwarm
jiuwenswarm-start
After launching, visit http://localhost:5173 to open the frontend.
From Source
git clone https://github.com/openJiuwen-ai/jiuwenswarm.git
cd jiuwenswarm
uv venv
uv pip install -e .
For detailed installation instructions, see: Install Guide
Quick Start
Configure Model
JiuwenSwarm supports multiple model platforms: Huawei Cloud MaaS, OpenAI, DeepSeek, DashScope, SiliconFlow, OpenRouter and other OpenAI-compatible APIs, as well as local model deployment.
A default model is the one piece of configuration you cannot skip. Set it in the web UI under More → Configuration, or edit ~/.jiuwenswarm/config/config.yaml directly. The file is created on your first jiuwenswarm-start, and saving it reloads the config without a restart.
For example, with DeepSeek：
model_name: deepseek-v4-flash
api_base: https://api.deepseek.com
api_key: sk-your-api-key
model_provider: OpenAI
Start a Conversation
The workbench has two spaces, switched from the top-left selector: Work, for office, collaboration, and general tasks, and Code, for viewing and modifying code in a project directory .
Each conversation runs in one of two execution modes, picked from the selector in the chat input area:
| Mode | What it does | Use it for |
|---|
| Agent mode | Single agent handles tasks independently, supports task planning and dynamic adjustment | Most daily tasks, Q&A, code generation, etc. |
| Cluster mode | Multi-agent collaboration mode, with a Leader orchestrating multiple specialized agents | Large, complex tasks that need multi-role collaboration |
Cluster Mode (default)
Example input:
This is the beginning of the README. Read the rest at the original. Read the full README ↗
