Remote VibeCode vs LLM Bench

RemoteVibeCode is an iPhone and iPad app for working with OpenAI Codex on a remote machine over SSH. Connect to your Linux, macOS, or Windows development machine, choose a project workspace, then start or resume Codex sessions from a focused mobile interface. You can type prompts, use iPhone voice-to-text, review Codex output, answer follow-up questions, queue additional prompts, and keep working against your remote codebase while away from your desk. RemoteVibeCode is designed for developers who already run Codex on a remote system and want a practical mobile client for real coding workflows. Depending on your selected Codex approval and permission mode, Codex can inspect files, make code changes, and run commands on the remote host. Features: - Connect to remote development machines over SSH - Manage multiple remote connections with connection tabs - Browse remote directories and select project workspaces - Start new Codex sessions or resume existing ones - Refresh available Codex models from the connected remote CLI - Choose model and execution profile per session - Type prompts or use iPhone voice-to-text - Queue follow-up prompts while Codex is still working - Review conversation history, final responses, and session output - See active work and unread result indicators across tabs - Inspect detached/background job status where supported - Export or share session transcripts - Save server, SSH key, and session settings for faster reconnects - Get setup guidance for Codex install, login, and updates Requirements: - A remote system accessible over SSH - Codex installed on that remote system - Codex signed in with a ChatGPT or OpenAI account - PowerShell, WSL, or another supported shell for Windows SSH targets

LLM Bench is an iOS test bench for developers comparing on-device LLM behavior under real device constraints. Run the same prompt against selected local model targets and compare the evidence before choosing what belongs in your app. LLM Bench focuses on practical signals: load time, first output time, generation time, output speed, memory, thermal state, model readiness, raw output text, failures, and saved run history. Use LLM Bench to: - Compare GPU-capable local model runs on iPhone and iPad. - Run repeatable prompts against selected model targets. - Inspect model output, timing, memory, and thermal state in one place. - Save benchmark runs for later review. - Export benchmark evidence as CSV. - Add models from Hugging Face URLs, direct file URLs, or local imports when the artifact format is supported. LLM Bench is built for technical builders who want a compact measurement tool, not a leaderboard or generic AI chat app. It helps you answer the practical question: which local model behaves well enough on this device for this use case? The free tier includes one completed benchmark run. Subscribing unlocks ongoing benchmarking, saved comparison work, and export workflows. Premium is available as an auto-renewing subscription (monthly or yearly), or a one-time Lifetime purchase. Payment is charged to your Apple ID at purchase; subscriptions renew automatically unless canceled at least 24 hours before the period ends. Manage or cancel anytime in your App Store account settings. Privacy Policy: https://thedandano.github.io/michilotl-studios-docs/apps/llm-bench/privacy/ Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/