AI gateway for managing AI and traditional APIs
Top 8.7% on sourcepulse
Higress is an AI-native API gateway designed for cloud-native environments, offering robust support for AI applications, LLM providers, and microservices. It targets developers and enterprises seeking a scalable, extensible, and secure gateway solution, providing unified management for AI and traditional API traffic with enhanced observability and control.
How It Works
Higress is built upon Istio and Envoy, leveraging their battle-tested capabilities for traffic management and proxying. Its core innovation lies in its Wasm plugin extensibility, allowing custom logic written in Go, Rust, or JavaScript to be sandboxed and executed within the gateway. This approach enables features like AI-specific traffic shaping, model load balancing, token rate limiting, and caching, while also facilitating the hosting of MCP (Model Context Protocol) Servers for AI agents to interact with various tools and services.
Quick Start & Requirements
docker run -d --rm --name higress-ai -v ${PWD}:/data -p 8001:8001 -p 8080:8080 -p 8443:8443 higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:latest
Highlighted Details
Maintenance & Community
Licensing & Compatibility
Limitations & Caveats
Gateway API support is noted as "coming soon," indicating potential migration effort from Ingress API. While Wasm plugins offer extensibility, managing multiple plugin versions and ensuring compatibility across different languages might require careful orchestration.
2 days ago
1 day