local-ai

NobodyWho: Local AI

Name: NobodyWho: Local AI
Author: nobodywho-ooo

Run LLMs locally and efficiently with NobodyWho. For founders needing on-device AI solutions.

1,019 stars70 forksRustQuality 9/10Updated 7/8/2026100% free · open source

What it does

NobodyWho lets you run large language models locally on your device, allowing for efficient and private AI processing without relying on cloud services.

Install / run

git clone https://github.com/nobodywho-ooo/nobodywho.git && cd nobodywho

When to use it

•When you need to integrate AI capabilities into a device with limited or no internet connectivity
•When protecting user data privacy is a priority and cloud-based AI solutions are not feasible
•When you want to reduce latency and improve real-time responsiveness in your AI-powered application

Quick start

1Build the NobodyWho inference engine by running the command `cargo build` in the terminal
2Prepare your LLM model for local inference, following the guidelines provided in the NobodyWho README
3Configure the `config.json` file to specify the model and other runtime parameters as needed
4Run the NobodyWho server using the command `cargo run` to start the local inference engine
5Test the setup by sending a request to the server using a tool like `curl` or a custom application

Ready-to-paste prompt

Use the following command to run a sample inference with a locally hosted model: `curl -X POST -H 'Content-Type: application/json' -d '{"input": "Your input text here"}' http://localhost:8080/infer`

Heads up: Ensure you have Rust and Cargo installed on your system, as NobodyWho is built using Rust and relies on Cargo for building and managing dependencies

Saves to your device