amux vs Agent Lab

Keep your AI coding agents running while you're away from your desk. amux is the remote control for your AI engineering fleet. Monitor live Claude Code, Codex, and Gemini sessions, approve pending actions, inspect terminal output, coordinate work across agents, and recover from problems directly from your iPhone. Think of it like GitHub Mobile for AI agents: the work happens on your laptop or server, amux puts the control panel in your pocket. WHAT YOU CAN DO FROM YOUR PHONE - Check overnight runs before getting out of bed - Approve permission prompts before agents stall - See exactly why an agent stopped (peek into live terminal output) - Assign a new task to an idle session - Send a steering instruction to redirect an agent mid-run - Monitor your whole fleet at once: status, active tasks, token usage - Manage the kanban board: see what's done, doing, and stuck - Keep coding while traveling BRING YOUR OWN SERVER amux is open source. Run the single-file Python server on your Mac, Linux box, or cloud VM, then connect this app over Tailscale, your LAN, or amux Cloud. Your code and agents never leave your infrastructure. BUILT FOR PARALLEL WORK Instead of babysitting one AI assistant, run a whole fleet. One agent per feature, per bug, per module, all supervised from a single dashboard. Self-healing keeps sessions alive: amux auto-compacts context, restarts on corruption, unblocks stuck prompts, and handles rate limits fleet-wide so your agents keep shipping overnight. TWO ACCESS MODES Native iOS app (this app): SwiftUI with optimized touch targets and full peek panel. Connects to your amux server over Wi-Fi, Tailscale, or the amux cloud tunnel. Progressive Web App: Open your amux dashboard URL in Safari and install to home screen for a full-screen experience without the App Store. REQUIREMENTS - amux server running on Mac or Linux (free, open source: github.com/mixpeek/amux) - Claude Code, OpenAI Codex CLI, or Gemini CLI installed on your server - Wi-Fi, Tailscale, or amux tunnel for remote access Learn more at amux.io

Agent Lab is a learning and experimentation playground for AI agents, built for AI learners, agent developers, and product managers. It doesn't just run agents — it makes every step of an agent's execution visible, so you can finally understand how agents actually work. Unlike an ordinary AI chat app, Agent Lab is about learning, experimenting, debugging, and visualization. On every run you can see the prompts, tool calls, retrieval, tokens, and latency — nothing is hidden. Get started fast · On-device local models: download a small Qwen model on first use (Wi-Fi recommended), then run it fully offline — no API key and no second machine required. Cost is always 0, and tokens and latency are shown for real. · Download on demand: grab other open-source models your device can actually run, with capability gating based on your chip and memory. · Cloud models: works with Chat Completions-compatible APIs (DeepSeek, Moonshot, OpenRouter, and more) and Anthropic Claude — just enter your key, base URL, and model. Three built-in demos · Customer Support Agent — demonstrates tool calling and workflow with a built-in mock order system, no real backend needed. · RAG Knowledge Base — comes with curated reference docs (LangGraph, MCP, LLM APIs, Python) and lets you upload your own PDF / Markdown / TXT, then inspect the retrieved chunks, similarity scores, and final answer. · Research Agent — shows how an agent plans on its own: Planner → Search → Read → Summarize → Answer. Unified visual debugging Every demo offers three views: · Timeline — the full step-by-step sequence of LLM and tool calls · Graph — the workflow graph, highlighting the active node as it runs · Console — expand any step to see System / User / Assistant prompts, the complete LLM request and response JSON, tool requests and responses, tokens, estimated cost, latency, and errors Security and privacy · API keys are stored encrypted on-device via the system Keychain — local only, never uploaded to any server. · Uploaded knowledge-base files and the vector indexes built from them stay on your device and can be deleted anytime. · On-device inference runs fully offline; your data never leaves the device. No sign-up, no login — open it and go. Make every step an agent takes visible.