Open-Source Intelligent Command Layer
Make local LLM inference faster with chunk-level KV cache reuse
NOW AVAILABLE on MICROSOFT STORE - Bulk-delete or move IMAP emails by AI Cleanup (NEW), sender, domain, or nested rules - CLI + Web GUI, stdlib-only Python. Gmail support, scheduling. Windows/Linux/MacOS supported platforms.
🎬 Nano Cinema: An all-in-one local AI video production studio. Automatically orchestrates Llama-3 (Script), SDXL-Turbo (Visuals), EdgeTTS (Audio), and LTX-Video (Motion) into a seamless Python workflow. Create cinematic short films with no API fees, full privacy, and professional-grade editing logic included!!! 🚀
An AI-powered Windows desktop code debugger and explainer that monitors your clipboard system-wide. Copy code anywhere, click the floating bubble, and get instant, local-first AI analysis with parallel web context enrichment.
Local-first Personal AI Memory OS - RAG over your entire life. Git, notes, calendar, location. 100% offline. No cloud.
An intelligent local AI agent powered by open-source LLMs, featuring free web search, hybrid memory, and context-aware query rewriting for real-time, grounded answers.
Free macOS dictation with local AI profiles — Wispr Flow alternative powered by Whisper + llama.cpp. No cloud, no subscription.
Local AI assistant that lives in your MacBook's notch. Powered by Ollama — chat, vision, web search, and an autonomous file-system Agent Mode (beta), all on-device.
HWP / HWPX files are a web-based editor that can be opened and edited directly in the browser. You can modify Hangul documents without installing any separate program, and even use local AI (OLLAMA) to get Korean synonym suggestions.
**LocalEcho** is a fully local, open-source Text-to-Speech engine powered by **Qwen3 TTS** models
One API. 20+ AI Providers. Smart Routing. Strong Security. Self-hosted OpenAI-compatible gateway with intelligent fallback & battle-tested defenses.
tripleF (3F) monorepo — an agentic, open-source AI workbench: conversation harness + dashboard, local-first via Ollama or Ollama Cloud.
LayerRun is a Rust-based local LLM runtime for memory-aware model execution, layer-wise loading, model inspection, and flexible inference serving.
Lightweight Ruby gem for interacting with locally running Ollama LLMs with streaming, chat, and full offline privacy.
Run model GGUF gui esay ,faster,localy 100%
Setup guide for AI-Mini PC. For hosting local LLM's via LM-Studio as RDP/headless-GUI Setup. In this example we'll use a Minisforum AI X1 Pro, AMD Ryzen AI 9 HX 370 / 64GB RAM
A lightweight, self-contained Python project for running a local large language model (LLM) with minimal dependencies. This system uses TinyLlama-1.1B-Chat-v1.0.0 and llama-cpp-python for inference, and Rich for a user-friendly console chat interface
Local AI desktop app built for a single user. No accounts. No teams. No telemetry. Just you and your models.
Description: All-in-one Windows desktop AI toolkit. Local model management, prompt library, batch processing, image generation helpers, text tools and productivity utilities. Clean interface, lightweight and regularly updated for creators and developers.
To associate your repository with the local-ai-llm topic, visit your repo's landing page and select "manage topics."