Pangolin 1.24 adds exit nodes, on-demand connections on Mac and iOS, an overhaul of the client UI on Mac and Windows, and a subnet router for Linux machine clients.

How to connect branch offices, stores, and factories to a cloud network or to each other with Pangolin subnet routers, using a hub and spoke model with no inbound firewall rules.

Build your own self-hosted VPN with Pangolin

Compare the best open source and self-hosted AI gateways in 2026, including LiteLLM, Bifrost, Pangolin, Portkey Gateway, and Kong AI Gateway.

Learn what an AI gateway is, how it sits between applications, agents, and models, and how it differs from API, LLM, and MCP gateways.

How we turned Pangolin from a single-box reverse proxy into a stateless, horizontally-scalable cluster.

Why an identity-aware proxy is harder to make highly available than a normal load balancer, and how to self-host one that stays up without sending traffic through someone else's cloud.

What makes a VPN highly available, why most self-hosted VPNs are a single point of failure, and three ways to get real HA remote access with Pangolin.

Pangolin 1.23 makes high availability and clustering self-service on Scale and Enterprise, adds sites to the Pangolin CLI, and improves the server admin panel and Resource Launcher.

Publish a private /metrics endpoint as an authenticated Pangolin resource and scrape it with Prometheus using HTTP Basic credentials, without opening inbound ports or standing up a VPN.

Move your team off shared and per-user virtual API keys and onto identity-based access for your AI gateway - no keys to generate, distribute, or rotate for human users.

Virtual API keys solve model routing and budgeting well, but they were never built to be an identity system. Here's where that gap shows up in self-hosted LiteLLM and Bifrost deployments, and what to do instead.

A general-purpose guide to putting any self-hosted model server - vLLM, Ollama, llama.cpp, LM Studio, LocalAI, or a private downstream gateway - behind Pangolin's identity-aware AI gateway.

Run open-weight models like DeepSeek, Qwen, and Kimi K2 on your own hardware, then reach them securely from anywhere through Pangolin's AI gateway - no API keys, no data leaving your infrastructure.

Give engineers and coding agents access to a self-hosted vLLM or Ollama cluster from one endpoint, authenticated by identity instead of API keys passed around a team.

Pangolin 1.22 introduces an AI Gateway for cloud and self-hosted models with identity-aware access. SSH, RDP, and VNC public resources, plus SSH and HTTPS private resources, are now available in Community Edition.