xmr.club search + submit independent · curated · graded

AI / LLMs — privacy-respecting options

LLM access without surveillance. Confidential-compute hosted (TEE), local runtimes, crypto-paid API gateways. Order matters: local first, then confidential-compute, then crypto-paid proxies, then mainstream APIs with email-only signup.

last reviewed 2026-05-13

jump: API · Uncensored Confidential Compute Local Runtime API · Multi-Provider Local Frontend API · Pay-Per-Use Multi-Channel Agents Coding Assistant ✕ clear subcat

filtered: subcat · local runtime ✕ clear all 4/11

› AI / LLMs — privacy-respecting options » Local Runtime 4

● Ollama

ANON FREE LOCAL NO-NETWORK

Run open-source LLMs locally — no network, no API key, no telemetry.

Open-source Self-host CLI API

Free · MIT · runtime + model weights local

Visit →

● llama.cpp

ANON LOCAL OPEN-SOURCE REFERENCE

C++ runtime for running LLMs locally on CPU + GPU. The backbone of every privacy-LLM stack.

Non-custodial Open-source Self-host CLI

Free · MIT · C++ · CPU/CUDA/ROCm/Metal

Visit →

● LM Studio

ANON LOCAL GUI OPENAI-COMPAT

Desktop GUI for local LLMs. Drag-drop GGUF models, OpenAI-compatible local API, no cloud.

Non-custodial Self-host API

Free for personal · MacOS/Win/Linux · localhost API

Visit →

● Jan

ANON LOCAL OPEN-SOURCE GUI

Open-source ChatGPT alternative running locally. Free, offline-first, model marketplace.

Non-custodial Open-source Self-host API

Free · MIT · MacOS/Win/Linux · OpenAI-compat API

Visit →

AI / LLMs — privacy-respecting options

Browse next — related categories