techjarves/Uncensored-Local-AI-Multiplatform

A cross-platform Flutter app that runs uncensored, 100% offline open-source AI models (GGUF) directly on your Android, iOS, or PC. No cloud, no filters, total privacy.

What it solves

This project provides a way to run open-source, uncensored AI models directly on mobile and desktop devices without relying on cloud services, subscriptions, or corporate safety filters.

How it works

Built using the Flutter framework and powered by the llama.cpp engine, the application allows users to download and run GGUF-format models locally. It manages model storage, provides a chat interface, and includes a built-in HTTP server that exposes an OpenAI-compatible API, enabling integration with other local tools and scripts.

Who it’s for

It is for users who want private, offline access to AI models without content restrictions or the need for an internet connection after the initial model download.

Highlights

  • Zero Censorship: Runs models that do not include corporate safety filters or refusals.
  • Total Privacy: All processing and conversation history remain entirely on the user's device.
  • Cross-Platform: Supports Android and iOS, with community-supported builds for Windows, macOS, and Linux.
  • Local API Server: Includes an OpenAI-compatible REST API for connecting to external applications.
  • Resource Monitoring: Displays real-time performance metrics like tokens per second and model loading progress.

Related

  • Project
    Nutlope/pdftochat

    PDFToChat is an open-source web app that enables users to interact with PDF documents through a chat interface. It uses retrieval-augmented generation, combining Chroma's hybrid vector search with Together AI's Mixtral model to provide accurate answers from the document content.

  • Project
    llm-jp/awesome-japanese-llm

    A community-curated summary of publicly available Japanese large language models and Japanese LLM evaluation benchmarks, with comparison details on release year, architecture, context length, training data, developer, and license. It helps researchers and developers quickly discover and compare Japanese-focused models while flagging which ones are not truly open source.

  • Project
    benman1/generative_ai_with_langchain

    This repository contains the code and practical guidance for building, testing, and deploying production-ready generative AI applications using LangChain and LangGraph.

  • Project
    microsoft/KBLaM

    KBLaM is a method for augmenting LLMs with external knowledge using trained adapters that transform knowledge bases into tokens, avoiding external retrieval and quadratic scaling issues.