Software · AI chatbots & assistants

goinfer

Pure-Go, no-cgo local LLM inference — run Gemma, Qwen, Llama and friends from safetensors or GGUF in a single static binary.

Completely free
Open source
No account

Overview

Features described in its GitHub repository: web interface and hardware acceleration.

Overview written by LicitPro from the documentation published by the authors and the cited sources; we have not tried the resource ourselves.

Excerpts that establish this information

“The one thing that reaches the network is fetching a model when you ask for one, from HuggingFace: pull, an hf: or demo: model reference, or the web UI's search and download.” — GitHub, 10 November 2026
“CPU, CUDA and Metal, cgo-free; WebGPU as an opt-in cgo build.” — GitHub, 10 November 2026

At a glance

All of goinfer is free: no feature is locked behind a paid plan, and its code is open.

Its licence (MIT) is a permissive open source licence: use, modification and redistribution are allowed, including in commercial projects.

Strengths

Open source code
No account needed
Commercial use allowed

Sources and checks

Facts collected from GitHub (credit card, account, source code, publisher, licence, free status, platforms, commercial use) — 9 November 2026
Last technical check: 8 November 2026
Description from github.com — Dépôt GitHub townsendmerino/goinfer (MIT)

How listings are built →

Do you develop goinfer?

Correct this listing with the report form, or cite it with this optional badge (it shows the verified free status and changes nothing in the ranking):

<a href="https://licitpro.fr/en/resource/goinfer"><img src="https://licitpro.fr/badge/goinfer.svg?l=en" alt="Listed on LicitPro" height="20"></a>

Developers and publishers →

In the same category

ChatGPT

AI tool

Bring ChatGPT to your desktop with ChatGPT Work and Codex, plus context from your email, screenshots, files, and anything on your screen.

Limited free planWinMacAndroidiOSWeb

Jan

Software · Open source

Jan is an AI chat assistant, available on Windows, macOS and Linux: local model execution, open-weight models (Llama, Mistral…), choice of several models and providers.

Completely freeWinMacLinux