Deploy vs The Abyss

On device private AI agents that live entirely on your iPhone. No accounts. No cloud. No tracking. Every conversation, every image, every document stays on your device — even with airplane mode on. Built for people who want a private ChatGPT or Claude alternative that works offline — without the account, the cloud round-trips, or the data harvesting. Pick an agent and start. Or build your own in five guided steps. — THE FIVE BUILT-IN AGENTS — Scout — your research agent. Searches the web with citations, summarizes findings, and remembers context across questions. Lens — your vision agent. Drop in a photo, screenshot, or whiteboard shot and ask anything about it. Ghost — your writing agent. Drafts, rewrites, edits, and shifts tone. The output reads like you, not like a chatbot. Vault — your document agent. Load PDFs, text files, or Markdown notes and ask questions. Answers cite the page they came from. Spark — your brainstorming agent. Pressure-tests ideas, runs lateral riffs, and breaks creative blocks. — BUILD YOUR OWN AGENT — A five-step guided wizard turns an idea into a working agent in under a minute. Choose its purpose, give it tools, pick a model, set its look. The on-device model writes its name, picks an emoji, and drafts the system prompt for you to approve. Unlimited custom agents. Each one keeps its own personality, its own toolset, and its own accent color. — TRUE ON-DEVICE AI — Powered by Apple's MLX framework with 4-bit quantized models that download once and then run forever, offline. Supported models include Qwen 3.5 in 0.8B, 2B, and 4B sizes — all multimodal with vision — plus Ministral 3B for fast text-only chat. More models are being added regularly, and we encourage you to contact us for requests. Pick the model that fits your iPhone. Switch any time. — FEATURES — · Streaming token output, native SwiftUI, dark-mode first · Per-agent accent colors and emoji · Extended thinking mode you can toggle per message · Web search via DuckDuckGo with proper citations · Native image understanding for screenshots, photos, and scans · Local document Q&A across PDF, TXT, and Markdown · VoiceOver, Dynamic Type, and Reduce Motion all fully supported — PRIVACY, FOR REAL — · 100% on-device inference. No model call ever leaves the iPhone. · No account. No sign-in. No email. · No analytics. No telemetry. No third-party SDKs reading anything. · Conversations, attached images, and uploaded documents stay on your device. · The only network call the app ever makes is your explicit web search, and only when you tap Scout. The privacy posture is a feature, not a marketing line. Your iPhone is the entire system. — REQUIREMENTS — iPhone running iOS 18 or later. Models download on first use; sizes range roughly from 600 MB to 3 GB depending on which model you pick. — SUPPORT — Questions, suggestions, bug reports: see the in-app Help screen.

The Abyss is the iOS companion for Hermes - your self-hosted AI agent running on your own machine. Connect over your local network or Tailscale, send prompts, watch the agent think and reach for tools in real time. The Abyss is a remote control. Hermes is the brain. You own both. Built for people who already host their own things. CHAT - Live token streaming. Watch the agent's reply appear as it's generated. - Transparent tool calls. See the agent reach into your shell, files, or the web - with each tool's name and arguments shown as a card. - Multimodal. Attach images from the photo library and send them with your prompt. - Slash commands. Trigger agent-side commands from a clean, keyboard-friendly composer. VOICE MODE - Hands-free conversation. Dictate prompts and hear the reply spoken back. - On-device transcription. Your voice is transcribed locally; the text is what gets sent to your agent. - Bring-your-own TTS. If your Hermes backend streams text-to-speech, you hear the agent in a neural voice; otherwise it falls back to iOS voices. SESSIONS - Server-side history. Every conversation lives on your own Hermes server, not ours. - Searchable, renameable, pinnable. Find the thread you need, give it a name, keep it on top. - Local cache. Scroll the transcript even when you're offline. MULTIPLE BACKENDS - Run more than one Hermes instance? Add them all. Switch active with one tap. - Pair a second device by scanning a QR code. Credentials never cross our servers - we don't have any. - Each backend gets its own identity colour so you always know which agent you're talking to. DEMO MODE - Not running Hermes yet? Try the demo. A scripted preview shows how the real client behaves, without any setup. No account, no network, no obligation. PRIVACY-FIRST BY DESIGN - All credentials live in iOS Keychain. Face ID required before revealing or sharing them. - No analytics. No third-party SDKs. No telemetry. - The Abyss only talks to the backends you point it at. Apple processes any future purchases; that's the only third party in the loop. - App data flows between your device and your own Hermes backend. Nothing else. REQUIREMENTS - A running Hermes Agent on a machine you control. - Network reachability to that machine. Same Wi-Fi works; Tailscale (or another mesh) is recommended if you want to reach the agent from anywhere. The Abyss is not a hosted AI service. It is a remote control for an AI agent you host yourself.