ArchSecurely handle, observe, and personalize LLM applications for building intelligent agents.

Arch

Arch is an intelligent prompt gateway designed to protect, observe, and personalize AI applications (agents). Built on (and by the core contributors of) Envoy Proxy with the belief that AI applications need nuanced handling, intelligent routing, robust observability, and integration with backend (API) systems for prompts are secured and opaque user requests, which require the same capabilities as traditional HTTP requests with backend (API) systems for LLMs.

Product Highlights

• Observability: Arch supports open observability standards to enable better tracing, metrics, and logs.
• Traffic Management: Arch manages LLM calls to prevent jailbreak attempts and ensure safe user interactions.
• Prompt Guard: Arch centralizes prompt guardrails to smart retry, automatic cutoff, and resilient upstream connections for continuous availability.

Use Cases

• Insurance Agent: Build a full insurance agent with Arch.
• Network Agent: Build a networking co-pilot/agent with Arch.
• Weather Forecast: Walk through of the core function calling capabilities of a arch gateway using weather forecasting service.

Target Audience

Arch is designed for developers building AI agents or applications that use large language models (LLMs).