Agentmux vs Google Agent Development Kit (ADK)

A side-by-side look at pricing, capabilities, pros, cons, and our editorial scores.

	Agentmux Agents	Google Agent Development Kit (ADK) Agents
Tagline	iOS command center for SSH, tmux, and AI coding agents	Google's open-source framework for building, evaluating, and deploying production AI agents
Category	Agents	Agents
Pricing	Freemium· 14-day full-feature trial; Free tier (single-server SSH, persistent sessions, core terminal); Pro tier (multi-server, custom agents, remote editing, advanced file/branch tools) — exact Pro price not published on landing page	Free· Framework itself is free and open-source (Apache 2.0). Costs come from the underlying model provider (e.g. Gemini API / Vertex AI usage) and any hosting infrastructure (Cloud Run, GKE, Agent Engine).
Model	Agent-agnostic front-end for Claude Code, OpenAI Codex, Gemini CLI, and OpenCode	Gemini (default) plus Claude, GPT-4/5, Llama, and other providers via LiteLLM
Editorial score	—	—
Use cases	Mobile supervision of long-running Claude Code sessionsKicking off Codex or Gemini CLI jobs from an iPhoneReattaching to tmux sessions after network changesRemote code review from an iPad on the goQuick SSH edits to config or source files from mobileManaging multiple dev servers from a single workspaceChecking build or agent output while away from a laptop	Multi-agent research assistantCustomer support triage agentRAG chatbot backed by Vertex AI SearchCode review and refactoring agentBigQuery natural-language analytics agentDocument processing pipelineVoice/streaming conversational agentInternal tool-use agent orchestrating APIsEvaluation and regression testing of LLM workflowsEnterprise workflow automation on Agent Engine
Pros	One-tap launch for Claude, Codex, Gemini, and OpenCode CLIs alongside a normal shell tmux-backed persistence survives network changes, sleep, and Wi-Fi-to-LTE handoffs Touch-friendly terminal UI purpose-built for iPhone and iPad rather than a generic SSH client Remote file browser with syntax highlighting for quick code review from mobile Pro tier adds a remote SSH editor, multi-server workspaces, and branch/file history tools Free tier is genuinely usable for single-server work, not just a demo 14-day full-feature trial exposes every Pro feature before committing	Genuinely open-source (Apache 2.0) with active Google engineering behind it, not a hosted-only product Multi-language: first-class Python, Java, and Go SDKs — rare among agent frameworks that are usually Python-only Built-in dev UI (`adk web`) with trace inspection, event stream, and session replay speeds up debugging enormously Model-agnostic via LiteLLM — Gemini is default but Claude, GPT, and local models plug in cleanly Rich multi-agent primitives out of the box: SequentialAgent, ParallelAgent, LoopAgent, and hierarchical sub-agents Tight Google Cloud integration for deployment (Cloud Run, GKE, Agent Engine) plus native BigQuery/Vertex Search tools Evaluation harness with trajectory-level scoring is included, not a separate paid add-on First-class MCP (Model Context Protocol) client and server support
Cons	iOS-only — no Android, macOS, or web client Does not run its own models; you must bring and configure the underlying agent CLIs on your own servers Pro pricing is not clearly published on the marketing site, making budgeting harder Small independent app with limited public track record versus established mobile SSH clients Typing serious code on a phone remains awkward regardless of UI polish, limiting deep sessions No documented public API or open-source code for extension or auditing	Documentation and examples lean heavily on Gemini + Google Cloud; non-Google paths work but feel like second-class citizens API surface is still evolving — breaking changes between minor versions have been common through 2025-2026 Multi-agent orchestration primitives are powerful but the graph/callback model has a real learning curve compared to a plain prompt loop Agent Engine deployment is convenient but locks you into GCP billing and quotas TypeScript/Kotlin support lags the Python SDK in features and community examples
Website	agentmux.saxcave.cc	google.github.io

Pick Agentmux if

✅ One-tap launch for Claude, Codex, Gemini, and OpenCode CLIs alongside a normal shell
✅ tmux-backed persistence survives network changes, sleep, and Wi-Fi-to-LTE handoffs
✅ Touch-friendly terminal UI purpose-built for iPhone and iPad rather than a generic SSH client
✅ Remote file browser with syntax highlighting for quick code review from mobile

Pick Google Agent Development Kit (ADK) if

✅ Genuinely open-source (Apache 2.0) with active Google engineering behind it, not a hosted-only product
✅ Multi-language: first-class Python, Java, and Go SDKs — rare among agent frameworks that are usually Python-only
✅ Built-in dev UI (`adk web`) with trace inspection, event stream, and session replay speeds up debugging enormously
✅ Model-agnostic via LiteLLM — Gemini is default but Claude, GPT, and local models plug in cleanly

Compare a different pair →