Intelligent gateway for
Solana agents
Turn simple APIs into powerful AI agents. Curve sits between your apps and AI services, making everything work together seamlessly.
Why Curve?
Curve is built on (and by some of the core contributors of) Envoy proxy with the belief that:
Prompts are complex and unclear user requests that require the same features as traditional HTTP requests, such as secure handling, smart routing, strong observability, and seamless integration with backend (API) systems for personalization; all separate from business logic.
Key features:
Out-of-process architecture, built on Envoy
Curve operates as an independent process running alongside your application servers. It enhances HTTP connection management, filtering, and telemetry features, specifically optimized for prompts and large language models (LLMs).
It is compatible with a wide range of programming languages, including Python, Java, C++, Go, PHP, and more.
Engineered with (fast) LLMs
Curve is engineered with specialized (sub-billion) LLMs that are designed for fast, cost-effective, and accurate handling of prompts. These LLMs are best-in-class for critical prompt-related tasks like:
-
Function Calling: Function-calling helps you personalize GenAI applications with your API operations via user prompts.
-
Prompt Guards: Centrally manages safety features to prevent toxic or jailbreak prompts.
-
Intent-drift detection: Able to detect shifts in user intent to improve retrieval accuracy and response efficiency.
Traffic Management
Curve offers several capabilities for LLM calls originating from your applications, including a vendor-agnostic SDK to make LLM calls, smart retries on errors from upstream LLMs, and automatic cutover to other LLMs configured in Curve for continuous availability and disaster recovery scenarios.
Curve extends Envoy’s cluster subsystem to manage upstream connections to LLMs so that you can build resilient AI applications.
Front/Edge Gateway
There is substantial benefit in using the same software at the edge (observability, traffic shaping algorithms, applying guardrails, etc.) as for outbound LLM inference use cases.
Curve is exceptionally well suited as an edge gateway for AI applications. This includes TLS termination, rate limiting, and prompt-based routing.
Built with <3 by the Curve Gateway team!