localized

Semantic level code search/indexer with tree-sitter parsing, Qdrant vector store, and Typer/FastAPI interfaces. Supports calling via MCP.

Local MCP Client is a cross-platform web and API interface for interacting with configurable MCP servers using natural language, powered by Ollama and any local LLM of choice, enabling structured tool execution and dynamic agent behavior.

端到端加密的剪切板共享方案/An end-to-end encrypted cross-platform clipboard tool

Local AI model reacts to hand gestures via camera and then automates actions to your specifications.

ReliaChat, is a frontend app designed to have the easisest UI elements and massive app language support to chat with a locally hosted LLM.

Ignis is a locally-ran AI assistant that combines advanced cognitive memory systems with dynamic personality evolution - all while maintaining complete privacy on your hardware.

A local, AI-powered photo search engine built with Python, CLIP, and ChromaDB.

Ask questions about any GitHub/Local repo in plain English — get answers backed by real code with file + line references. Self-hosted RAG for codebases. Runs fully local with Ollama.

Local metal-accelerated Whisper transcription pipeline for Apple Silicon

This repo shows the coding of air pollution LLM advisor chatbot for localized LLM using Ollama

Tool to create bilingual subtitles to videos: syncing, translating, editing

Intelligent Document Assistant - User can ask questions from any uploaded document

AI-powered animation teaching assistant for kids aged 10–17. 12 Principles of Animation, localized for Kenya's ocean wildlife.

Locally generate chemical structure by IUPAC naming scheme.

A local PDF converter CLI: images, text, markdown, HTML and office formats in and out of PDF, plus merge/split/rotate/compress and OCR. Nothing leaves your machine.

Local finance tracking software I made to keep track of hours worked and payments owed

Desktop application that enables natural language querying of PDF documents using Retrieval-Augmented Generation (RAG). Built with Python, Ollama, and local LLMs - all processing happens on the user's machine with zero cloud dependencies, ensuring complete privacy.