ArchGW Open Source AI Proxy for Intelligent Agent Routing
ArchGW is an intelligent proxy server designed as an edge and AI gateway for agents, handling prompts and network traffic with built-in guardrails and routing capabilities.
Adil, Salman, and Jose, the team behind ArchGW, have introduced an open-source proxy server designed to streamline AI agent development. Built on Envoy Proxy, ArchGW acts as an edge and AI gateway, handling prompts with native intelligence for routing, safety, and integration.
Why ArchGW?
Building production-ready AI agents involves repetitive low-level tasks like:
- Applying guardrails to filter unsafe or off-topic requests.
- Clarifying vague inputs to prevent agent errors.
- Routing prompts to the right expert agent based on context.
- Integrating new LLMs safely and efficiently.
ArchGW consolidates these tasks into a dedicated infrastructure layer, freeing developers to focus on business logic rather than plumbing code.
Key Features
- Listener Subsystem: Manages ingress/egress request processing.
- Prompt Handler: Uses
prompt_guardfor safety checks andprompt_targetfor routing decisions. - Model Serving: Hosts lightweight LLMs for tasks like hallucination detection.
The team leverages Task-specific LLMs (Hugging Face models) for intelligent operations.
Team Background
The founders bring expertise from:
- Envoy Proxy (Lyft)
- AWS API Gateway
- Microsoft Research (NLP models)
- Meta (safety systems)
Get Started
- Demo: YouTube
- Docs: ArchGW Documentation
- Community: Discord
ArchGW is written in Rust and aims to accelerate AI agent development with safety, scalability, and personalization at its core.
Related News
AWS extends Bedrock AgentCore Gateway to unify MCP servers for AI agents
AWS announces expanded Amazon Bedrock AgentCore Gateway support for MCP servers, enabling centralized management of AI agent tools across organizations.
CEOs Must Prioritize AI Investment Amid Rapid Change
Forward-thinking CEOs are focusing on AI investment, agile operations, and strategic growth to navigate disruption and lead competitively.
About the Author
Dr. Lisa Kim
AI Ethics Researcher
Leading expert in AI ethics and responsible AI development with 13 years of research experience. Former member of Microsoft AI Ethics Committee, now provides consulting for multiple international AI governance organizations. Regularly contributes AI ethics articles to top-tier journals like Nature and Science.