Pad Code AI vs Peak Pocket AI

Turn ideas into working code on iPad and iPhone. Pad Code AI brings an editor, local code runners, a terminal and project tools into one workspace. WRITE AND RUN Run C, C++, Python, JavaScript, TypeScript, Ruby, PHP, Lua and SQLite queries on your device with bundled compilers and interpreters. Use interactive input, command-line arguments and project files. Preview HTML and CSS projects. Language and library support depends on the included runtime. EDIT AND ORGANIZE Work with syntax highlighting, find in files, individual-file replacement, code folding and snippets. Open project folders through Files, manage multiple files, review Git changes, commit and push, and export projects as ZIP. SMARTER EDITING AND GIT SYNC Code completion suggests keywords, types and names from your file as you type, and works with VoiceOver. Pull changes from GitHub: edits made on both sides are merged line by line, and overlapping lines are marked for you to choose. Your projects also appear in the Files app. AI, WHEN YOU WANT IT Ask for explanations, refactoring ideas, tests or fixes. Review suggested changes before applying them. On-device AI requires a compatible system and device with Apple Intelligence enabled. Optional third-party AI requires your own credentials and an internet connection; availability varies by region. You choose what context to share. LEARN AND BUILD ANYWHERE Practice programming, try small scripts and develop project ideas. Local code execution works offline; Git network operations and remote AI require internet access. The interface is available in 20 languages. Support: https://phamhungtien.com/PadCodeAI PREVIEW SUPPORT Preview HTML, CSS and browser JavaScript with WebKit. Swift/SwiftUI, Metal and native OpenGL visual previews are not supported. Swift and other unsupported languages are editing-only. WORKSPACE AGENT With a compatible configured provider, the optional Workspace Agent can inspect code, create and edit text files, rename or delete files, and run supported code inside the project you open. Agent Changes shows saved changes, before/after diffs and Undo. The app checks for intervening edits before writing or restoring. You explicitly enable access and choose what context to share. Provider credentials are your own; multi-step requests may incur additional provider charges. This is a bounded project workflow, not an unrestricted system shell or package installer. New editor color themes and a refined interface. Git over HTTPS now supports GitHub, GitLab, Bitbucket and compatible servers, using standard repositories with branches, commits, stash, push and pull. Python can import compatible packages, including NumPy and pandas. Package downloads require internet; not every PyPI package is supported. Programs using only the bundled standard library can run offline. Improved language icons and links to video guides. Start faster with ready-to-run Python, web, C and JavaScript project templates.

Peak Pocket AI is a lab for language models that run on your iPhone. Chat privately with open models, then look under the hood: how fast they generate, how confident they are in every word, how well they remember a long prompt, and how your phone holds up under sustained load. PRIVATE BY DESIGN Models run on the device. Your chats, notebook, photos, and settings never leave your iPhone. No account, no analytics, no ads. Once a model is downloaded, everything works in airplane mode. A LAB NOTEBOOK FOR EVERY GENERATION Every reply is recorded with its seed, settings, timings, and device state. Rerun any run with identical settings and see whether the output reproduces, character for character. Export runs as CSV or JSON, or as a signed report that anyone can check for changes. LIVE TELEMETRY Watch tokens per second, time to first token, memory, and thermal state as a reply streams in. SEE WHAT THE MODEL WAS THINKING Confidence shading shows how sure the model was of each word. Tap any word to see the alternatives it nearly chose, with their probabilities. Reasoning models show their thinking above the answer. EVALUATIONS Score models on built-in question sets for knowledge, math, tool calling, and structured JSON output, or import your own. Compare two models on the same questions with confidence intervals. EXPERIMENTS Run the same prompt and seed across models or settings. Measure how speed and memory change as the context fills, and test long-context recall: hide a fact at different depths of a long prompt and chart how often the model finds it. ENDURANCE AND ENERGY Measure what sustained generation does to your phone: throughput over time, throttling, thermal state, and battery used. An energy-per-token estimate is shown when a run is measured on battery. VISION AND APPLE'S ON-DEVICE MODEL Ask vision models about a photo, processed on the device. On iPhones with Apple Intelligence, chat with and evaluate Apple's built-in model alongside open models. BRING YOUR OWN MODELS Browse Hugging Face for GGUF models with a fit estimate for your phone's memory, including gated models with your access token. Optionally connect an OpenAI-compatible provider with your own API key; remote chats are clearly marked. MAKE IT YOURS Four themes in light and dark, including High Contrast, a colorblind-safe confidence scale, science personas, and share cards for any run or comparison. Built by Peak Summit Labs.