RepoAlerts
SponsorGet alerts

T-Crypt/berth

Get alerts like thisView on GitHubShare on X

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 9 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change today.

  • Licence OK

    Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

A Go daemon that brokers access to a single NVIDIA GPU. Engines such as chat, image and voice servers lease the card in turn, queued by priority, so they do not load together and run out of memory. Includes a gateway, model downloads and a read-only status UI.

Who it's for

Developers and home-lab users running several local AI engines on one NVIDIA GPU

How to use it

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up T-Crypt/berth in my project. Follow its README: https://github.com/T-Crypt/berth. Explain each step and check it is safe before running anything.

Read the README

Star curve

84From 0 to 84 stars between 11 Oct 2026 and 20 Oct 2026.

Alternatives

Similar projects named in its profile. Each link searches the directory.

Get alerts for repos like this

We'll email you when something in Dev infrastructure starts rising. Free, once a week, only what matches.

18,263 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![T-Crypt/berth on RepoAlerts](https://repoalerts.com/badge/T-Crypt/berth.svg)](https://repoalerts.com/repo/T-Crypt/berth?ref=badge)
Share on X
  • Lore-Hex/token-exchange-neocloud-in-a-box

    Open-source toolkit for running a small confidential GPU inference server: a model runs inside an Intel TDX confidential VM with NVIDIA GPUs in confidential-computing mode, exposed through an OpenAI-c

    Dev infrastructurePython · 52 stars · +52 this week · 2 days old

  • cobanov/PS5LM

    Runs llama.cpp on a jailbroken PS5, using the console GPU through Vulkan to load GGUF models. Serves OpenAI and Anthropic compatible APIs over the local network, plus a chat page, a decision model end

    Models & inferenceC++ · 607 stars · +517 this week · 19 days old · HN 375 pts

  • oneo-me/onevra

    Go component library for native desktop applications, built on MyGo. Provides themed controls, window shells, Lucide icons, and composed components such as chat, Markdown, charts and a command palette

    Apps & desktopGo · 242 stars · +219 this week · 14 days old

  • ThinkWatchProject/ThinkWatch-Lite

    Local gateway that sits between AI clients such as Claude Code and Codex and their upstreams. It lets upstreams and models be switched in the gateway alone, records each request with its cost and rout

    Dev infrastructureTypeScript · 804 stars · +549 this week · 38 days old

  • tashfeenahmed/freellmapi

    A self-hosted gateway that exposes one OpenAI-compatible /v1 endpoint in front of many free LLM provider tiers. It stores provider keys encrypted, routes each request to an available model, fails over

    Models & inferenceTypeScript · 38,176 stars · +3,542 this week · 182 days old

  • eliasbiondo/antirion

    A Rust AI gateway shipped as one binary with a built-in web console. It sits between applications and LLM providers such as OpenAI, Anthropic, Gemini and Bedrock, routing, securing, budgeting and logg

    Dev infrastructureRust · 140 stars · +140 this week · 3 days old