# Vibra-Ingenn/Janus

> Local LLM server in Go: runs .gguf models via llama.cpp (Vulkan or CPU) and exposes an OpenAI-compatible API with a web UI and built-in tools.

- Magnitude: 3.8 out of 10 — Early signal
- Stars: 22 total · +0 stars today, ≈ 25 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Go · License: MIT · Created: 2026-09-24 · Last push: 2026-10-01
- GitHub: https://github.com/Vibra-Ingenn/Janus · Page: https://gitnova.dev/en/r/Vibra-Ingenn/Janus

## Useful for

- Run a local model and call it from Cursor or Cline via the OpenAI-compatible endpoint
- Hot-swap .gguf models in the web UI without restarting the server
- Run tool-calling tasks (files, commands, OCR) through the Kernel tab

## Why it’s here

- 0 stars so far today, about 25 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 8 days old and already has 22 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia” — 44 points, 3 h ago.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 0
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 7 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 8

## Stars per day, last 13 days (oldest → newest, today is partial)

2026-09-20 … 2026-10-02: 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 25, 0

## Magnitude by day, last 2 days

10-01 2.6, 10-02 3.8

## Hacker News

- Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia — 44 points, 4 comments: https://news.ycombinator.com/item?id=49926773

## Spotted in now

- Spotted on Hacker News

## Similar by description

1. **AtomicBot-ai/Atomic-Chat** — 1.1 · Steady · Language models · TypeScript · +0 stars today, ≈ 6 by evening
   Desktop app and local inference engine for running open-weight LLMs (Llama, Gemma, Qwen, Mistral, etc.) on your own machine, exposing an OpenAI-compatible API at localhost:1337/v1.
   Full card: https://gitnova.dev/en/r/AtomicBot-ai/Atomic-Chat.md
2. **router-for-me/CLIProxyAPI** — 2.6 · Steady · AI agents · Go · +0 stars today, ≈ 57 by evening
   A proxy server that wraps CLI tools (Antigravity, ChatGPT Codex, Claude Code, Grok Build) as an OpenAI/Gemini/Claude/Codex-compatible API, letting you reach models from any compatible client or SDK.
   Full card: https://gitnova.dev/en/r/router-for-me/CLIProxyAPI.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-02 00:11 UTC, updated every 30 minutes.