1. Project Overview

Lynxe Introduction (formerly: JManus)

Lynxe is a Java implementation of Manus, which has been widely used in many applications within Alibaba Group, mainly used for processing tasks with certain determinacy requirements, such as quickly finding data from massive data and converting it into a database row, or analyzing logs and giving alarms, etc.

2. Open Source License

Licensed under Apache-2.0

3. Screenshots

4. Feature Overview

Lynxe Product Features

Pure Java Manus implementation:

Pure Java multi-agent collaboration implementation, providing complete HTTP call interfaces, suitable for Java developers to do secondary integration.

Func-Agent mode:

Accurate control of each step execution details, providing extremely high execution determinacy and completing complex repetitive processes and functions. See Lynxe Case Set- Func-Agent Case for details.

MCP integration:

Native support for Model Context Protocol, realizing seamless integration with external services and tools.

5. Tech Stack

Quick Start

Starting and running Lynxe in 5 minutes:

Preconditions

• DashScope API key
   (or alternative AI model provider)
• ☕ Java 17+ (for running JAR files or source code running) or Docker (for containerized deployment)

Method 1: Using GitHub Release (recommended)

Download and run JAR file

Manual download: You can also directly access the Lynxe Releases page to manually download the latest version of the JAR file.

Accessing the application

After the application starts, access http://localhost:18080 in the browser.

Guided setup: After the application starts, the guided page will be automatically displayed. Select the language in the first page and input the DashScope API key you just applied in the second page to complete the configuration.

Congratulations! Your multi-agent system has been quickly started.

Method 2: Using Docker (recommended for production environment)

Pull and run Docker image

# Pull the latest version of Lynxe Docker image
docker pull ghcr.io/spring-ai-alibaba/lynxe:v4.7.0
# Run the container
docker run -d \
  --name lynxe \
  -p 18080:18080 \
  ghcr.io/spring-ai-alibaba/lynxe:v4.7.0

Method 3: Running from source code (optional)

See the README.md documentation for details