Nobodywho provides a lightweight SDK that simplifies the integration of GGUF-format large language models into applications. It offers a one‑line, asynchronous API for loading local models and generating chat completions, with language bindings for Python, Swift, and Godot, enabling developers to add on‑device AI dialogue to desktop, web, or game projects with minimal boiler‑plate.
Funding
Funding not disclosed
Founders
Product
Problem
Developers often need to integrate large language models into applications but face challenges with complex setup, model loading, and handling asynchronous responses, especially when working with local GGUF model files.
Solution
Nobodywho offers a lightweight SDK that abstracts model management and provides a simple, asynchronous API for loading GGUF-format language models and generating chat completions. The library supports multiple programming languages and integrates with popular development environments, allowing developers to instantiate a Chat object from a model path and query it with natural language prompts. Responses are delivered through promise‑based or signal‑driven callbacks, enabling seamless incorporation of AI-driven dialogue into desktop, web, or game applications without extensive boiler‑plate code.
Target Audience
Target users are software developers and AI engineers building applications that require on‑device language model inference, such as chatbots, interactive games, and productivity tools.
Features
- One‑line model initialization from a local GGUF file (e.g., `Chat.fromPath(modelPath: "./model.gguf")`)
- Asynchronous `ask` method returning a completed response object for easy await/then handling
- Language bindings for Python and Swift/Godot, facilitating cross‑platform development
- Event‑driven callbacks (`response_updated`, `response_finished`) for real‑time UI updates in game engines
- Minimal dependencies and straightforward installation via standard package managers