An AI gateway and production stack for generative AI builders that provides a unified API to access over 1,600 large language models. The platform includes tools for observability, guardrails, governance, and prompt management to help AI teams move from prototyping to production. It features a real-time observability dashboard to monitor model behavior, manage usage proactively, and catch anomalies early. The software is available as an open source project and is used by AI teams to manage LLM orchestration and caching to reduce costs. It is deployed as a centralized layer that eliminates the need to hard-code prompts or manually integrate multiple different models. The platform supports various deployment configurations to accommodate different organizational needs. It is used by over 3,000 generative AI teams to maintain production reliability.
Whether you want to cut software costs or escape vendor lock-in, these open source alternatives to Portkey give you an option you fully own. You can self-host them, so your data stays on infrastructure you control. This page lists 3 open source alternatives to Portkey. The most popular are Manifest, Helicone and Envoy AI Gateway. Most use the Apache-2.0 or MIT license, and 3 offer an official Docker image.
A smart model router that connects AI agents to multiple providers through a single OpenAI-compatible endpoint.
Log, monitor, and debug large language model applications with a unified gateway for AI model routing.
A gateway for routing application traffic to generative AI services with support for over sixteen LLM providers.
Join our newsletter to get shiny new open source software delivered to your inbox. Unsubscribe anytime.