Envoy AI Gateway v0.1.x
🎉 The First Official Release!
v0.1.0
This foundational release establishes Envoy AI Gateway as a production-ready solution for managing AI services in Kubernetes environments, providing the essential building blocks for enterprise AI infrastructure.
Installation
For installation instructions, see our Getting Started Guide.
✨ Core Features
Unified LLM Provider API
Complete support for OpenAI's GPT models with chat completions and embeddings
Native integration with AWS Bedrock for Claude, Titan, and other foundation models
Automatic translation between different provider APIs for consistent experience
Traffic Management & Rate Limiting
Intelligent rate limiting based on actual token consumption rather than request count
Weighted routing and load balancing across multiple AI service backends
Fine-grained traffic management at the route level with flexible matching
Kubernetes Native Integration
Native Kubernetes CRDs for AIGateway, AIServiceBackend, and routing configuration
Kubernetes operator for automated lifecycle management and configuration
Full integration with Kubernetes RBAC for secure access control
API Design
The v0.1.x series establishes the core API design for Envoy AI Gateway:
- Initial API Design: Core CRDs including AIGateway, AIServiceBackend, and AIGatewayRoute
- Gateway API Integration: Built on top of Kubernetes Gateway API specifications
- OpenAPI Schema: Complete OpenAPI v3 schema for all custom resources
📦 Dependencies Versions
Built with Go 1.22 for optimal performance and security
Built on Envoy Gateway for proven data plane capabilities
Leveraging Envoy Proxy's battle-tested networking capabilities
Implementing latest Gateway API standards
⏩ Patch Releases
v0.1.5
Bug Fixes
- ExtProc Image Syncing: Fixed external processor image synchronization issues
- Container Registry: Improved container image handling and registry integration
v0.1.4
Bug Fixes
- AWS Validation: Fixed validation error handling for AWS Bedrock requests
- Error Response Format: Improved error response formatting for better debugging
v0.1.3
New Features
Observability Enhancements
- GenAI Metrics: Added comprehensive metrics for AI service performance and usage tracking
Bug Fixes
- Chat Completion Streaming: Fixed streaming response handling for chat completions
- Metrics Collection: Resolved issues with metrics collection and reporting
v0.1.2
Bug Fixes
- Image Tag Fixes: Fixed rotator and ExtProc container image tag synchronization
- Deployment Stability: Improved deployment reliability and image pulling
v0.1.1
Bug Fixes
- AWS CLI Tools: Fixed authentication issues with AWS Bedrock integration
- Configuration Validation: Improved validation for AWS-specific configuration parameters
🙏 Acknowledgements
The v0.1.0 release represents months of collaborative effort from our founding community. Special thanks to early contributors and adopters who helped shape the initial architecture and provided invaluable feedback during the alpha and beta phases.
This milestone release sets the foundation for Envoy AI Gateway's future growth and establishes our commitment to providing enterprise-grade AI service management capabilities.
🔮 What Came Next
The success of the v0.1.x series paved the way for v0.2.0, which introduced:
- Azure OpenAI Integration
- Sidecar Architecture for Better Performance
- Cross-Backend Failover and Retry Logic
- Enhanced CLI Tools
v0.1 is now complete
The v0.1.x release is now complete. For the latest features and improvements, check out v0.2.