higress-group/himarket

HiMarket is an enterprise-level "AI Capability Marketplace and Developer Ecosystem Hub." It is not merely a simple aggregation of traditional APIs, but rather a comprehensive platform that packages, publishes, manages, and operates core AI assets such as enterprise Model APIs, MCP Servers, Agent APIs, etc., through standardized product formats.

Java

1,307

956 commits

updated Oct 10, 2026

See the code

README

HiMarket Logo

HiMarket AI Open Platform

English | 简体中文

License Release Stars Ask DeepWiki

Website   |   Docs   |   Deployment   |   Contributing

What is HiMarket?

HiMarket is an enterprise-grade AI open platform built on Higress AI Gateway, helping enterprises build private AI capability marketplace to uniformly manage and distribute AI resources such as LLM, MCP Server, Agent, and Agent Skill. The platform encapsulates distributed AI capabilities into standardized API products, supports multi-version management and gray-scale release, includes a built-in Skills Marketplace for developers to browse and install Agent Skills, provides HiChat AI conversation and HiCoding online programming for self-service developer experience, and features comprehensive enterprise-level operation capabilities including security control, observability analysis, metering and billing, making AI resource sharing and reuse efficient and convenient.

As enterprises scale their AI adoption, they face common challenges: fragmented model usage across teams, security risks from uncontrolled public model access, difficulty in measuring AI costs and SLA, and complex permission management. HiMarket addresses these by providing a unified AI entry point for the entire organization — connecting AI producers and consumers through a standardized marketplace.

Capabilities
CategoryFeatureDescription
AI MarketplaceModel MarketplaceIntegrate various models with content safety, token rate limiting, and other protection capabilities
MCP MarketplaceIntegrate MCP Servers from various platforms, support converting external APIs to standard MCP Servers
Agent MarketplacePackage and publish Agent applications, integrate with AgentScope and other Agent building platforms
Skills MarketplaceUpload and distribute Agent Skills, developers can browse, subscribe, and install Skill packages
Worker MarketplacePackage, version, and distribute Agent Workers that can be loaded with Skills; supports Nacos batch import and CLI installation
AI Experience CenterHiChat ConversationSingle-model conversation and multi-model comparison, MCP tool invocation testing, enhanced features like web-connected Q&A
HiCoding Online ProgrammingIntegrated secure sandbox environment, supporting Vibe Coding and human-AI collaborative development with real-time file changes and code preview
Enterprise ManagementProduct ManagementAuthentication, traffic control, call quotas, and other protection capabilities
ObservabilityFull-chain monitoring, call tracing, heatmaps, anomaly alerts
Metering & BillingToken-based call counting with automatic cost statistics
Version ManagementMulti-version parallel operation, gray-scale release, quick rollback
CustomizationPortal BrandingCustom domain, logo, color scheme, page layout
Identity AuthenticationSupport third-party OIDC integration with enterprise identity systems
Approval WorkflowConfigurable auto/manual approval for subscription and product scenarios
Product CatalogCustom category tags with browsing, filtering, and search support

System Architecture

HiMarket System Architecture
System Architecture

HiMarket system architecture consists of three layers:

  1. Infrastructure: Composed of AI Gateway, API Gateway, Higress and Nacos. HiMarket abstracts and encapsulates underlying AI resources based on these components to form standard API products for external use.
  2. AI Open Platform Admin: Management platform for administrators to create and customize portals, manage AI resources such as MCP Server, Model, Agent, and Agent Skill, including setting authentication policies and subscription approval workflows. The admin portal also provides observability dashboard to help administrators monitor AI resource usage and operational status in real-time.
  3. AI Open Platform Portal: Developer-facing portal site, also known as AI Marketplace or AI Hub, providing one-stop self-service where developers can complete identity registration, credential application, product browsing and subscription, online debugging, and more. Developers can also interact with models and MCP Servers through HiChat, or perform online AI programming in secure sandboxes through HiCoding.
HiMarket Admin Portal
Admin Dashboard
HiMarket Developer Portal
Developer Portal

Quick Start

Option 1: Local Setup

Requirements: JDK 17, Node.js 18+, Maven 3.6+, MySQL 8.0+

Start Backend:

Configure database connection (add to ~/.env or export directly):

export DB_HOST=localhost
export DB_PORT=3306
export DB_NAME=himarket
export DB_USERNAME=root
export DB_PASSWORD=your_password

Build and start with one command:

make run
# Or run the script directly: ./scripts/run.sh
# The script auto-loads ~/.env, compiles, stops old processes, starts in background, and waits until ready
# Backend API: http://localhost:8080

Start Frontend:

# Start admin portal
cd himarket-web/himarket-admin
npm install
npm run dev
# Admin portal: http://localhost:5174

# Start developer portal
cd himarket-web/himarket-frontend
npm install
npm run dev
# Developer portal: http://localhost:5173
Option 2: Docker Compose

Requirements: Docker, Docker Compose

Script Deployment: Use the interactive install.sh script to deploy the full stack (HiMarket, Higress, Nacos, MySQL) with guided configuration.

git clone https://github.com/higress-group/himarket.git
cd himarket/deploy/docker
./install.sh

AI Deployment (Recommended): If you're concerned about environment compatibility issues during deployment, we recommend using AI Coding tools such as Cursor, Qoder, or Claude Code, which can automatically detect and resolve environment problems. After cloning the project, simply enter in your AI tool:

Read the deployment docs under deploy/docker and help me deploy HiMarket with Docker Compose

See the Deployment Guide for details.

Service URLs after deployment:

Uninstall:

./install.sh --uninstall
Option 3: Helm Chart

Requirements: kubectl (connected to a K8s cluster), Helm

Script Deployment: Use the interactive install.sh script to deploy HiMarket to a Kubernetes cluster with guided configuration.

git clone https://github.com/higress-group/himarket.git
cd himarket/deploy/helm
./install.sh

AI Deployment (Recommended): If you're concerned about environment compatibility issues during deployment, we recommend using AI Coding tools such as Cursor, Qoder, or Claude Code, which can automatically detect and resolve environment problems. After cloning the project, simply enter in your AI tool:

Read the deployment docs under the deploy directory and help me deploy HiMarket to my K8s cluster with Helm

See the Deployment Guide for details.

Uninstall:

./install.sh --uninstall
Option 4: Cloud Deployment (Alibaba Cloud)

Alibaba Cloud ComputeNest supports out-of-the-box deployment of the community edition with one click:

Deploy on AlibabaCloud ComputeNest

Community

Join Us

DingTalk Group
DingTalk Group
WeChat Official Account
WeChat Official Account

Contributors

Thanks to all the developers who have contributed to HiMarket!

contributors

Star History

Star History Chart

higress-group/himarket

HiMarket is an enterprise-level "AI Capability Marketplace and Developer Ecosystem Hub." It is not merely a simple aggregation of traditional APIs, but rather a comprehensive platform that packages, publishes, manages, and operates core AI assets such as enterprise Model APIs, MCP Servers, Agent APIs, etc., through standardized product formats.

Java

1,307

956 commits

updated Oct 10, 2026

See the code

README

HiMarket Logo

HiMarket AI Open Platform

English | 简体中文

License Release Stars Ask DeepWiki

Website   |   Docs   |   Deployment   |   Contributing

What is HiMarket?

HiMarket is an enterprise-grade AI open platform built on Higress AI Gateway, helping enterprises build private AI capability marketplace to uniformly manage and distribute AI resources such as LLM, MCP Server, Agent, and Agent Skill. The platform encapsulates distributed AI capabilities into standardized API products, supports multi-version management and gray-scale release, includes a built-in Skills Marketplace for developers to browse and install Agent Skills, provides HiChat AI conversation and HiCoding online programming for self-service developer experience, and features comprehensive enterprise-level operation capabilities including security control, observability analysis, metering and billing, making AI resource sharing and reuse efficient and convenient.

As enterprises scale their AI adoption, they face common challenges: fragmented model usage across teams, security risks from uncontrolled public model access, difficulty in measuring AI costs and SLA, and complex permission management. HiMarket addresses these by providing a unified AI entry point for the entire organization — connecting AI producers and consumers through a standardized marketplace.

Capabilities
CategoryFeatureDescription
AI MarketplaceModel MarketplaceIntegrate various models with content safety, token rate limiting, and other protection capabilities
MCP MarketplaceIntegrate MCP Servers from various platforms, support converting external APIs to standard MCP Servers
Agent MarketplacePackage and publish Agent applications, integrate with AgentScope and other Agent building platforms
Skills MarketplaceUpload and distribute Agent Skills, developers can browse, subscribe, and install Skill packages
Worker MarketplacePackage, version, and distribute Agent Workers that can be loaded with Skills; supports Nacos batch import and CLI installation
AI Experience CenterHiChat ConversationSingle-model conversation and multi-model comparison, MCP tool invocation testing, enhanced features like web-connected Q&A
HiCoding Online ProgrammingIntegrated secure sandbox environment, supporting Vibe Coding and human-AI collaborative development with real-time file changes and code preview
Enterprise ManagementProduct ManagementAuthentication, traffic control, call quotas, and other protection capabilities
ObservabilityFull-chain monitoring, call tracing, heatmaps, anomaly alerts
Metering & BillingToken-based call counting with automatic cost statistics
Version ManagementMulti-version parallel operation, gray-scale release, quick rollback
CustomizationPortal BrandingCustom domain, logo, color scheme, page layout
Identity AuthenticationSupport third-party OIDC integration with enterprise identity systems
Approval WorkflowConfigurable auto/manual approval for subscription and product scenarios
Product CatalogCustom category tags with browsing, filtering, and search support

System Architecture

HiMarket System Architecture
System Architecture

HiMarket system architecture consists of three layers:

  1. Infrastructure: Composed of AI Gateway, API Gateway, Higress and Nacos. HiMarket abstracts and encapsulates underlying AI resources based on these components to form standard API products for external use.
  2. AI Open Platform Admin: Management platform for administrators to create and customize portals, manage AI resources such as MCP Server, Model, Agent, and Agent Skill, including setting authentication policies and subscription approval workflows. The admin portal also provides observability dashboard to help administrators monitor AI resource usage and operational status in real-time.
  3. AI Open Platform Portal: Developer-facing portal site, also known as AI Marketplace or AI Hub, providing one-stop self-service where developers can complete identity registration, credential application, product browsing and subscription, online debugging, and more. Developers can also interact with models and MCP Servers through HiChat, or perform online AI programming in secure sandboxes through HiCoding.
HiMarket Admin Portal
Admin Dashboard
HiMarket Developer Portal
Developer Portal

Quick Start

Option 1: Local Setup

Requirements: JDK 17, Node.js 18+, Maven 3.6+, MySQL 8.0+

Start Backend:

Configure database connection (add to ~/.env or export directly):

export DB_HOST=localhost
export DB_PORT=3306
export DB_NAME=himarket
export DB_USERNAME=root
export DB_PASSWORD=your_password

Build and start with one command:

make run
# Or run the script directly: ./scripts/run.sh
# The script auto-loads ~/.env, compiles, stops old processes, starts in background, and waits until ready
# Backend API: http://localhost:8080

Start Frontend:

# Start admin portal
cd himarket-web/himarket-admin
npm install
npm run dev
# Admin portal: http://localhost:5174

# Start developer portal
cd himarket-web/himarket-frontend
npm install
npm run dev
# Developer portal: http://localhost:5173
Option 2: Docker Compose

Requirements: Docker, Docker Compose

Script Deployment: Use the interactive install.sh script to deploy the full stack (HiMarket, Higress, Nacos, MySQL) with guided configuration.

git clone https://github.com/higress-group/himarket.git
cd himarket/deploy/docker
./install.sh

AI Deployment (Recommended): If you're concerned about environment compatibility issues during deployment, we recommend using AI Coding tools such as Cursor, Qoder, or Claude Code, which can automatically detect and resolve environment problems. After cloning the project, simply enter in your AI tool:

Read the deployment docs under deploy/docker and help me deploy HiMarket with Docker Compose

See the Deployment Guide for details.

Service URLs after deployment:

Uninstall:

./install.sh --uninstall
Option 3: Helm Chart

Requirements: kubectl (connected to a K8s cluster), Helm

Script Deployment: Use the interactive install.sh script to deploy HiMarket to a Kubernetes cluster with guided configuration.

git clone https://github.com/higress-group/himarket.git
cd himarket/deploy/helm
./install.sh

AI Deployment (Recommended): If you're concerned about environment compatibility issues during deployment, we recommend using AI Coding tools such as Cursor, Qoder, or Claude Code, which can automatically detect and resolve environment problems. After cloning the project, simply enter in your AI tool:

Read the deployment docs under the deploy directory and help me deploy HiMarket to my K8s cluster with Helm

See the Deployment Guide for details.

Uninstall:

./install.sh --uninstall
Option 4: Cloud Deployment (Alibaba Cloud)

Alibaba Cloud ComputeNest supports out-of-the-box deployment of the community edition with one click:

Deploy on AlibabaCloud ComputeNest

Community

Join Us

DingTalk Group
DingTalk Group
WeChat Official Account
WeChat Official Account

Contributors

Thanks to all the developers who have contributed to HiMarket!

contributors

Star History

Star History Chart

Significant stargazers

Eric Wang

31 followers · starred Dec 2025

yanlinly

135 followers · starred Aug 2025

uuuyuqi

11 followers · starred Sep 2025

LearningGp

16 followers · starred Sep 2025