Fully local, offline speech-to-text dictation that types into any app using on-device Parakeet models and optional Ollama cleanup: zero telemetry, no cloud, and completely free.
Local AI
Category: Local AI under Artificial Intelligence
Local-first AI voice studio powered by Qwen3-TTS and six more engines. Clones voices and synthesizes speech fully on your machine, with no per-character metering, though your own GPU does the work.
AGPL-3.0 personal cloud OS: a sandboxed K3s app platform for self-hosting files, services, and local AI on hardware you own. Trade-offs are a dedicated-hardware footprint and AGPL network copyleft.
AGPLv3-or-commercial image toolkit: 50+ tools plus local AI for background removal, upscaling, and OCR in one Docker container. Images never leave your hardware. SaaS embedding needs a paid license.
MIT voice-to-text dictation that runs Whisper and Parakeet models fully on-device: hotkey, speak into any app, nothing leaves your machine. Cloud sync, agent mode, and SSO sit behind paid tiers.
Local-first AI desktop assistant that keeps your "second brain" in an Obsidian-style Markdown vault and on-device SQLite. Optional local Ollama models, no cloud account. GPL-3.0, single-founder beta.
Apache 2.0 LLM fine-tuning framework from Unsloth AI: 2x faster training on 60% less VRAM versus standard implementations; multi-GPU and full-parameter training require Pro/Enterprise tiers.
A local-first, autonomous AI coding agent for secure app building without sending proprietary code to uncertified SaaS backends.
GPL-3.0 AI-first note-taking app: a self-hosted second brain with RAG-powered recall on your own hardware, unlike cloud-bound Mem.ai. Built for personal knowledge management, not team collaboration.
MIT-licensed AI coding agent, model-agnostic across 75+ providers. Runs in terminal, desktop, or IDE without Anthropic-only lock-in.
The all-in-one desktop AI application for RAG, AI Agents, and No-Code automation. Run LLMs locally with full data privacy.
Open-source toolkit for parsing complex documents (PDF, DOCX, HTML) into structured JSON/Markdown, purpose-built for Generative AI and RAG ingestion pipelines.
Local AI meeting assistant with zero cloud audio transit and full transcript ownership, for executives and legal teams where discussions cannot leave the device.