Observer AI vs Local LLM runner

Create AI agents that watch your screen, camera, or listen to audio, and take action when something happens. Observer AI lets you build intelligent micro-agents powered by local LLMs. Your agents can monitor your digital environment and automatically send notifications through Discord, Telegram, WhatsApp, SMS, Email, Phone calls, or Pushover. HOW IT WORKS 1. Choose Sensors: Screen capture, camera, microphone, clipboard, or audio 2. Pick a Model: Connect to local models via Ollama, llama.cpp, vLLM, or use cloud inference 3. Set Actions: Configure notifications, memory logging, or video recording when conditions are met EXAMPLE USE CASES - Person detection alerts via Telegram when someone appears on camera - Smart screen monitoring that notifies you when specific content appears - Meeting transcription and logging - Custom automation triggered by visual or audio cues NOTIFICATION CHANNELS - Discord - Telegram - WhatsApp - SMS - Email - Phone calls (VoIP) - Pushover - Browser notifications PRIVACY-FIRST DESIGN Observer AI is 100% open source. Run entirely local with your own inference server and Discord webhooks, zero data touches our servers. For maximum privacy, compile from source and use local models. FEATURES - Visual and audio sensor inputs - Local LLM support (Ollama, llama.cpp, vLLM, LMStudio) - Cloud inference option for convenience - Agent memory system for context retention - Video clip recording and marking - Community agent sharing - Background operation OPEN SOURCE Full source code available at https://github.com/Roy3838/Observer App Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Platform Terms of Service: https://observer-ai.com/#/terms Privacy Policy: https://observer-ai.com/#/privacy

Run LLM on your iPhone, 100% local, no network (Network needed once to download a model) Models: • Qwen2.5 0.5B Instruct — ~0.4 GB (4 GB RAM) • Llama 3.2 1B Instruct — ~0.8 GB (4 GB RAM) • Qwen2.5 1.5B Instruct — ~0.9 GB (4 GB RAM) • Llama 3.2 3B Instruct — ~1.9 GB (6 GB RAM) • Qwen3 4B Instruct 2507 — ~2.5 GB (6 GB RAM) • Qwen2.5 7B Instruct — ~4.4 GB (8 GB RAM) Also: • Add your own GGUF (for example, from Hugging Face) • Auto-estimated max context from GPU memory; you can change it Requires iOS 18 or later. Tested on iPhone 11, 14 Pro, 15 Pro with iOS 26. Qwen models © Alibaba Cloud. Licensed under Apache License 2.0. Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Built with Llama. On-device inference uses llama.cpp (MIT License).