Sidecar ML vs SSH Terminal & SFTP

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.

ChatSSH is a private local LLM command planner and SSH client. Describe the task you want to complete, get a structured command plan generated on your device, review the exact commands, then run them in Terminal. PRIVATE LOCAL AI FOR SSH The AI planner works with an on-device language model. Your request and generated command plan remain on your device instead of being sent to a cloud AI service. A compact profile supplies the connected host's operating system, architecture, shell, and working directory so syntax can fit the server. Passwords, private keys, and terminal history are never added to the request. Ask for a plain-language outcome such as checking storage, finding a process, inspecting a service, reading logs, or preparing a careful sequence of shell commands. ChatSSH turns the request into a compact plan with the exact command first and a short explanation below it. The model is a planner, not an automatic operator: every proposal is visible for review before it is run. CHOOSE YOUR LOCAL MODEL Gemma 4 E2B is the faster default model for everyday SSH command planning. Gemma 4 E4B is an optional higher-capability download in Local Models. Choose an installed default in Settings, or select another installed model for an individual AI workspace. REVIEW BEFORE EXECUTION Read the complete command and its explanation, then run one command or the full plan. Commands that may change data, require elevated permissions, or have a critical effect are labeled. Review is the default. Auto-Run is optional and requires an explicit warning because shell commands can be destructive. Starting a proposed command immediately moves the workflow to Terminal; standard output, errors, and exit results remain in Terminal rather than in AI Chat. AN SSH WORKSPACE, NOT JUST A CHAT Create a host with its name, hostname, port, and user name, then open one focused workspace for that computer. Credentials, connection settings, and trusted fingerprints stay on your device. A new or changed host key is surfaced for review. Use Terminal for direct shell work, practical keys, output, and errors. Use Files to inspect remote directories, show hidden items, navigate folders, and download files you choose. One live workspace keeps Terminal, Files, and the draggable Local AI panel together without reconnecting or leaving the selected host. MAKE THE PLANNER YOURS Choose from five app styles, select the in-app language, set terminal text size, choose command execution behavior, and edit the planner system prompt. Settings also provides local-model management, reset-to-defaults, and purchase restoration. FREE USE AND UNLIMITED LOCAL AI Terminal access, saved hosts, credentials, and remote files are available without a subscription. Free local AI planning returns each local calendar day, and only a delivered plan uses that day's allowance. Cancellation or failure does not consume it. ChatSSH Unlimited unlocks unlimited private, on-device command planning with the monthly subscription. The localized product name, duration, and price are shown before purchase. ChatSSH is for people who understand the computers they connect to and review commands before execution. It does not guarantee that a generated command is safe, correct, or appropriate for every system. Check the proposed command, its risk label, and its expected effect before running it, and keep reliable backups where changes matter. SUBSCRIPTIONS: - A monthly subscription unlocks unlimited private, on-device command planning. - The subscription automatically renews every month unless auto-renew is turned off at least 24 hours before the end of the current period. - Payment is charged to your Apple Account at confirmation of purchase. - You can manage or cancel the subscription in your App Store account settings. - Restore Purchases is available in the app. Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Privacy Policy: https://yumcut.com/mobile/privacy