
APIPark is a self-hosted AI gateway and developer portal for teams that need to manage access to models and business APIs in one place. It connects Ollama alongside cloud providers such as OpenAI, Claude, Gemini and DeepSeek. The gateway runs on your infrastructure; requests to cloud providers still go to those services.
Its standardized API gives applications a common interface across model providers. Teams can combine a model with a prompt template to publish a dedicated REST API, such as translation or sentiment analysis, and share it through the developer portal. Changing models or prompts doesn't require changing the application's request format. APIPark also provides access to MCP services.
Access management covers application identities, API keys and approval workflows. Service managers can approve requests for particular APIs, apply permissions across teams or clients, and control consumption with quotas and rate limits. A masking engine identifies sensitive information in requests and responses. Usage reports track API calls and token consumption by team and project, while request logs can be exported to external logging platforms.
APIPark also supports businesses selling access to their models and APIs, with usage billing, settlement and revenue reports. Distributors can operate API stores with their own domains and branding. The open-source project uses the Apache 2.0 license and is free for commercial use. It supports cluster deployment, load balancing and failover between models.
Claim this page with an email at apipark.com. APIPark gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find APIPark?Promote it
Something wrong or outdated on this page?
1.2KUpdated 1 day agoMIT
macOS · Windows · Linux · Docker · Web#Guardrails#llama.cpp backend#LLM tracing
GoModel is a self-hosted AI gateway for developers and platform teams that want one API for local models and cloud providers. It accepts OpenAI- and Anthropic-compatible requests, so applications can keep their existing SDKs while the gateway handles provider selection and usage controls.
9.5KUpdated 1 day agoApache-2.0
Docker · Web#Guardrails#MCP#Tool calling
59.9KUpdated 56 minutes ago
#Guardrails#MCP#Multi-user access
1.2KUpdated 2 years agoMIT
Docker#Guardrails#Multi-user access#OpenAI-compatible API
44.2KUpdated 2 days agoApache-2.0
#MCP
Kong Gateway puts API, LLM and MCP traffic behind a shared gateway on your own infrastructure. It's for platform teams that need consistent access controls and traffic policies across services and AI applications. The open-source gateway uses the Apache 2.0 license and runs natively on Kubernetes through Kong's official Ingress Controller.
7.1KUpdated 2 days agoApache-2.0
Docker#Guardrails#LLM tracing#Multi-agent workflows
Higress is a self-hosted AI gateway for developers and teams managing model APIs and the tools their AI agents call. It puts LLM traffic and MCP servers behind a shared entry point, with authentication, traffic controls and monitoring. The open-source edition uses the Apache 2.0 license and runs locally in Docker without registration. Alibaba Cloud also offers a fully managed gateway.
LiteLLM gives platform teams one place to manage access to LLMs across providers. Its self-hosted AI gateway puts cloud services and internal or locally hosted models behind an OpenAI-compatible API, so applications can change models without changing their integration. Developers can also use its Python SDK directly.
BricksLLM is a self-hosted AI gateway for teams that need to control access and spending across LLM applications. It sits between applications and model providers, applying cost and rate limits to individual API keys. The gateway is open source under the MIT license and runs locally or on your server through Docker, with PostgreSQL and Redis.
Plano, formerly Arch Gateway, is a self-hosted AI gateway for developers building applications with multiple agents or model providers. It puts routing, guardrails and request tracing in a separate service, so each agent doesn't need its own implementation of that infrastructure. It's open source under Apache 2.0.