#on-device

Free, local voice dictation for Windows and Mac. Hold a key, speak, your words appear at the cursor. On-device Whisper, no cloud, no account, no telemetry.

Hear a short spoken summary after your coding agent answers. Free to install - no API keys, no subscription, no cloud TTS.

A free, local, open-source alternative to Wispr Flow. Hold a hotkey, talk, and your words are typed into any Windows app — on-device Whisper/Nemotron speech-to-text with optional local LLM cleanup. No cloud, no account.

Android personal knowledge graph app - smart exocortex v3.0 (end-side AI + ambient capture + zero-anxiety)

Several models in one conversation, routed by a policy: any modelpact providers you name — Ollama, OpenAI, on-device — plus Claude from the terminal you already pay for

Private, on-device meeting assistant for macOS. It records, transcribes, identifies who spoke, and writes a structured summary, entirely on your machine.

A tool-calling agent: a loop over sessions the library already owns modelpact

14-modality on-device capture (screen/audio/input), OCR, and semantic search for AI agents.

An open on-device agent engine for Android: three inference runtimes (llama.cpp CPU / MLC GPU / cloud), hot-mount LoRA, evidence-gated memory & skills, RSI harness

Run LLMs on Apple devices with CoreML, optimized for Apple Neural Engine + GPU