Explore live open-source projects and AI models.

Fully offline personal chatbot with local LLM, speech-to-text (Whisper), and text-to-speech (Kokoro) support.

USB-portable offline AI assistant. AES-256 encrypted history, Turkish-tuned LLM (Trendyol), RAG over PDF/DOCX. KVKK uyumlu, %100 offline.

An Eclipse plugin that supports offline and online LLMs/AIs with an integration into eclipse itself. Based on langchain4j including support for Ollama, LM Studio, Claude, Mistral, github copilot etc. Offline or online as we like.

Artifact for Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization

Offline database schema context for LLM agents. Extract once, serve via MCP — no live DB needed.

J.A.R.V.I.S. — Local AI Assistant for KDE Plasma 6 A privacy-focused, offline digital assistant inspired by Iron Man. Features integrated LLM chat via llama.cpp, voice commands with whisper.cpp, Piper TTS, and real-time system monitoring. Built with C++ and QML for seamless Plasma integration.

LinkedIn LLM Post Generator – Generate high-quality, professional LinkedIn posts completely offline using a fine-tuned open-source model (TinyLLaMA-1.1B-Chat). Built with PEFT + LoRA on Apple M3, this project requires no cloud APIs and supports themes like internships, promotions, certifications,... Read more

DomainMind: Enhance Local LLMs with RAG DomainMind integrates Retrieval-Augmented Generation (RAG) with local Large Language Models (LLMs) to answer domain-specific questions using a custom knowledgebase. It ensures privacy by running entirely offline and adapts LLMs to specialized fields like s... Read more

Transcribe Offline by openresearchtools.com is an open source desktop application that allows you to transcribe audio and video fully offline, with optional speaker diarisation and word-level alignment. It can also generate subtitles and integrate with local large language models (LLMs) for summa... Read more

Turn your Android phone into an offline OpenAI-compatible local server. Expose on-device LLMs (like Gemma) to your local network via a HTTP API.