ReqKit Http Client vs Neuro

ReqKit is a native HTTP client for developers, QA engineers, and API builders who want a focused request tool on iPhone and iPad. Create HTTP requests with query parameters, headers, authentication, and request bodies. Inspect status codes, timing, size, response headers, and formatted response bodies. Save useful requests into collapsible collections and drag requests between them. ReqKit is local-first. Requests, environments, collections, and history remain on your device. Sensitive environment values can be stored in Apple Keychain and are omitted from exported backups. Key features: - GET, POST, PUT, PATCH, DELETE, HEAD, and OPTIONS - Query parameters, headers, request bodies, auth, timeout, and redirects - JSON, raw text, URL-encoded form, and multipart form bodies - Bearer Token and Basic Authentication - Formatted response body and header inspection - Response status, duration, and size - Collapsible, renameable request collections with drag and drop - Request history - Environment variables using `{{variable}}` syntax - Sensitive environment values stored in Keychain - Import from curl and copy as curl - Local JSON backup import and export - iPhone and iPad support No account, subscription, analytics, or ReqKit cloud service is required.

Neuro lets you fine-tune real AI language models directly on your iPhone — no cloud, no servers, no data leaving your device. Pick a base model from the built-in catalog, choose a dataset (or bring your own), and train a specialized version tuned to your task. Everything runs locally using Apple's Neural Engine and GPU, powered by RWKV — an efficient architecture built for on-device use. FEATURES • Browse and download open models and datasets • Five training intensity levels, from light head-tuning to deep fine-tuning • Real-time training progress: loss, accuracy, memory usage • Fully offline — your data never leaves your device • Free and open source Neuro is built for people who want to experiment with real machine learning on real hardware, without renting a GPU or sending data anywhere. Whether you're a student, a researcher, or just curious how fine-tuning works, Neuro gives you a hands-on, private way to do it. This is an early release — expect rough edges, and expect it to get better. Feedback and contributions are welcome on GitHub.