TerminaLLM vs Sidecar ML

TerminaLLM is a mobile workspace for the remote machine where your command-line AI runs. Connect to where an agent is already working, keep going on sessions that survive every disconnect, and now run a whole team of agents at once. SWARM: A TEAM OF AI AGENTS, RUN FROM YOUR PHONE Launch a crew on your own server and watch it work. A lead architect breaks the job into pieces and hands them out, while the agents you choose run side by side, each in its own live terminal pane. • Start from a recipe: Debugging, Code review, Add tests, Refactor, Implement a feature, or Write docs. • Run any agent: presets for Claude Code, Codex, and Aider, or your own command, each with its model and effort. • Each pane is a real terminal, not a log tail. Read it, type into it, take over any time. • Agents run on your machine, signed in with your own AI CLI logins. Your prompts and your code never pass through us. Swarm is a Pro feature. It needs a small helper daemon, which the app can install for you (one tap on supported servers). SESSIONS THAT DO NOT DROP • Persistent sessions survive disconnects, Wi-Fi to cellular handoffs, and app backgrounding, running whether you are watching or not. • Termina-TCP, an optional helper daemon, gives sub-second reconnects. It falls back to plain SSH automatically. • Get a push notification the moment a long run stops for input, across the major AI coding CLIs. SEE AND STEER YOUR WORK • The Changes tab tracks every file that changes, with line counts, diff previews, and one-tap export. • Full SFTP browser with code, image, video, and audio previews, plus an in-app code editor. • Voice dictation two ways: platform streaming, or on-device Whisper that keeps audio on the phone. • OAuth and login URLs open in an in-app browser, so you never leave the session. • Live Activities show SSH status on the Lock Screen and Dynamic Island. SECURITY THAT IS SERIOUS BY DEFAULT • Encrypted credential vault (AES-256-GCM with HKDF-Expand), opt-in and on-device only. • TOTP two-factor, Face ID and Touch ID, host key verification, and an exportable audit log. • Three security profiles (Paranoid, Casual, Speedster) tune lockouts and timeouts. • TLS public-key pinning on our proxy, plus encrypted backup and restore. FREE, WITH A DAILY TASTE OF PLUS Free includes the SSH terminal, SFTP browser, the Changes tab, voice dictation, media drop, the full security suite, and 5 connection profiles, plus a daily taste of every Plus feature: code editor (15 KB, 3 saves per day), session recording (30-second clips), session sharing (1 per day), port forwarding (1 tunnel, 30-minute cap), batch SFTP (3 files per batch, 2 batches per day), 2 SFTP bookmarks, and 1 encrypted backup per month. PLUS, $4.99/month: removes every Free cap, and adds multi-hop SSH through bastion hosts (jump host) and unlimited connection profiles. PRO, $9.99/month: everything in Plus, plus Swarm, the AI Assistant chatbot, and voice-to-command translation. GENERATIVE AI DISCLOSURE The Pro AI Assistant chatbot and voice-to-command translation use Anthropic's Claude API. Your prompts and the recent chatbot conversation are sent to Anthropic, PBC. SSH credentials, terminal output, command results, file contents, and file paths are never sent. Explicit consent is required before any data leaves your device, and you can revoke it in Settings > Security. Swarm is different: it orchestrates the AI coding tools already installed on your own server, under your own logins. Swarm prompts and code are never sent to us or to Anthropic by the app. SUBSCRIPTION TERMS Plus and Pro are auto-renewable subscriptions. Payment is charged to your Apple ID at confirmation of purchase. Subscriptions renew for the same length and price unless auto-renew is turned off at least 24 hours before the current period ends. Manage or cancel in iOS Settings > [your name] > Subscriptions. Terms of Use (EULA): https://terminallm.app/terms Privacy Policy: https://terminallm.app/privacy

Turn your iPhone into a private, on-device AI server for your whole network. Sidecar ML runs a lightweight HTTP server on your iPhone that exposes Apple's built-in machine-learning models to any device on your local network. Tap Start Server, scan the QR code, and your Mac, PC, Raspberry Pi, or browser can call powerful on-device AI over plain REST — no cloud, no accounts, no API keys, no usage fees, and no data leaving your network. Everything runs on the phone. Nothing is uploaded to a server and there's nothing to pay for. (The one exception, music recognition, matches against Apple's catalog and tells you so up front.) ONE IPHONE, A DOZEN AI CAPABILITIES • Chat with the on-device large language model through a chat-completions endpoint that's compatible with the popular OpenAI API format — streaming, JSON mode, and structured output included. Point existing tools and SDKs at your phone and they just work. • Generate images from a text prompt in a choice of art styles. • OCR — pull text out of photos, receipts, and screenshots with per-line boxes and multi-language support. • Read barcodes and QR codes (EAN, Code128, and more). • Classify images across roughly a thousand categories, or produce image embeddings for similarity search. • Remove backgrounds and isolate subjects or people as clean PNG cut-outs. • Detect faces and facial landmarks, body pose, and hand pose. • Scan documents with automatic edge detection and perspective correction. • Convert speech to text and text to speech, with a wide range of voices (including Personal Voice). • Translate text between languages completely offline. • Analyse text: language, sentiment, named entities, tokens, and embeddings. • Classify sounds across hundreds of categories, or identify the music that's playing. BUILT FOR DEVELOPERS AND MAKERS • Clean REST + Server-Sent Events API — call it from curl, Python, JavaScript, or any HTTP client. • Chat endpoint compatible with the OpenAI format, so many existing tools and SDKs work unchanged. • Automatic discovery on your network via Bonjour. • Honest capability reporting: ask the server what it can do and it tells you exactly what's available on your device, and why. • Optional bearer-token authentication to lock the server down on shared networks. FREE WEB CONSOLE AND CODE EXAMPLES A ready-to-use web console — plus Python examples, a command-line client, and full API documentation — is free and open-source. Download the single-file console and browse the source here: https://github.com/AndersFB/Sidecar-ML-Console/ Open the console in any browser, enter your phone's address, and try every capability with a friendly UI — nothing to install. GOOD TO KNOW • The on-device large language model and image generation require an Apple Intelligence-capable iPhone. The other capabilities run on a much wider range of devices. • The server runs while the app is in the foreground; a keep-awake option helps during longer sessions. • Some features (offline translation language pairs and certain speech models) download their models on first use. Turn the iPhone in your pocket into a private AI endpoint for your projects, your home lab, and your prototypes — Sidecar ML.