Janus API Router icon
Janus API Router icon

Janus API Router

Janus is a single Go binary that runs .gguf models on your machine and exposes an OpenAI-compatible API. Point Cursor, Cline, or any local or cloud LLM, or AI tool with compatible OpenAI API endpoints at localhost — no Python, no Docker.

Cost / License

  • Free
  • Open Source (MIT)

Platforms

  • Windows
  • Linux
  • Mac
0likes
0articles
Save

Features

Properties

  1.  Privacy focused

Features

  1.  No Tracking
  2.  Ad-free
  3.  Works Offline
  4.  No Coding Required
  5.  No registration required
  6.  Local AI
  7.  Golang
  8.  Multi Platform

Janus API Router News & Activities

Highlights All activities

Recent activities

Janus API Router information

AlternativeTo Categories

Development, AI Tools & Services

GitHub repository

  •  37 Stars
  •  0 Forks
  •  1 Open Issues
  •   Updated  
View on GitHub

Popular alternatives

View all
Janus API Router was added to AlternativeTo by Paul Tracey on and this page was last updated .

No comments or reviews, maybe you want to be first?

Official Links

What is Janus API Router?

Janus is a single Go binary that runs .gguf models on your machine and exposes an OpenAI-compatible API. Point Cursor, Cline, or any local or cloud LLM, or AI tool with compatible OpenAI API endpoints at localhost — no Python, no Docker.

Features:

  • Local inference via llama.cpp with Vulkan GPU support (AMD, Intel, NVIDIA) or CPU fallback (much slower)
  • OpenAI-compatible API at /v1/chat/completions and /v1/models
  • Hot-swap models without restarting the server
  • Chat template auto-detection from GGUF metadata
  • Thinking model support — splits <think> blocks into reasoning_content
  • OpenRouter fallback for cloud models when needed
  • Built-in model downloader for Hugging Face

GPU recommended for usable speeds. CPU works but will be extremely slow. No CUDA required — Vulkan handles AMD, Intel, and NVIDIA equally.

MIT licensed. Built for developers who want local inference without the setup tax.