Codeium self-hosted enterprise backend lets the popular IDE plugin run fully on your hardware.
Editorial verdict: “Best 'enterprise Copilot' replacement when self-hosting is mandatory. Paid tier.”
Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"
For teams that must keep code off third-party clouds, Codeium’s self-hosted backend is the most polished way to get Copilot-grade autocomplete without data leaving your network. The IDE plugins—VS Code, JetBrains, Neovim—are identical to the cloud version, just pointed at your own GPU server. You’ll need at least 24 GB VRAM per node for the fine-tuned model that ships with the enterprise tier, and the setup is well-supported, not an afterthought. The catch: this is a paid enterprise product only, and the closed-source backend means your team can’t audit what’s running on your hardware.
Plugin for VS Code, JetBrains, Vim, etc.
Pre-filled with this app's recommended use case + budget tier. Get the full rig + runtime + model picks.
The full directory — filter by category, runtime, OS, privacy posture, or VRAM.
What this app talks to: Ollama, vLLM, llama.cpp, MLX, LM Studio. The upstream layer.
Did this app work for you on a specific rig? Submit the benchmark — it powers the model + hardware pages.