Agent Lab vs AgentCmd
Price, ratings, monetisation and update history for both apps, side by side — with what reviewers say about each.
Agent Lab
Explore and understand AI agents with this interactive playground. Visualize every step of an agent's execution, including prompts, tool calls, and latency. Experiment with on-device or cloud models for learning and debugging.
- Visualize agent execution steps
- On-device local models
- Cloud model integration
- Built-in demo agents
- Unified visual debugging (Timeline, Graph, Console)
- Secure on-device data storage
Read full descriptionHide full description
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.
AgentCmd
Read full descriptionHide full description
AgentCmd is a native remote control for the Qwen Code CLI's server (qwen serve) that runs on your own computer. Start the server in your project, pair your phone by scanning the QR code it prints, and drive your coding agent from anywhere on your network — or over a VPN or tunnel. It speaks the CLI's own protocol, so the phone shows exactly what the desktop does: • Live transcript — prompts, the agent's thinking, streamed replies, and every tool call as it happens, with token counts and timings. • Approvals on the go — approve or reject file edits and shell commands, with the diff or command right there. Choose how much to auto-approve per session. • Full agent toolbox — switch model and reasoning effort, browse and @-reference files, attach photos or files, and reach Plugins, Channels, Scheduled Tasks, Goals and workspaces. • Pick up any conversation — your sessions are listed newest-first; open one and its history is restored. • Notifications — get told the moment a task finishes, fails, or needs your approval, even while the app is in the background. • Yours end to end — the agent runs on your machine and this app talks only to it. No account, no analytics, nothing sent to us. Access tokens live in the device keychain; unencrypted HTTP is allowed only to local/private addresses. Requires the Qwen Code CLI (Node.js 22+) running qwen serve on your computer. Not sure yet? A built-in Demo shows a complete session offline, no server needed. AgentCmd is an independent client. It is not affiliated with, endorsed by, or sponsored by Alibaba or the Qwen team.
Screenshots
Verdict
The clearest difference is in-app purchases: AgentCmd at none against Agent Lab's 4. AgentCmd also leads on device support (3 vs 1) and iOS requirement (16.4 vs 18.0). On price, update cadence and ads there is nothing between them.
Scored on Price · Rating · Positive reviews · Number of ratings · Update frequency · Ad data · In-app purchases · Monetization · Best chart rank · Devices · Requires iOS
Both are free to download. Agent Lab sells 4 one-off in-app purchases. AgentCmd asks for nothing beyond the download.
Agent Lab ships an update every 3 weeks, AgentCmd every 10 days. The most recent releases landed on November 18, 2026 and November 21, 2026 respectively.
| Parameter | Agent Lab | AgentCmd |
|---|---|---|
| Price | Free | Free |
| Rating | 5.0 (1 ratings) — better | — |
| Number of ratings | 1 — better | — |
| Update frequency | Every 3 weeks | Every 10 days — better |
| Ad data | No | No |
| In-app purchases | Yes | No — better |
| Monetization | Free | — |
| Devices | iPhone | iPhone, iPad, Apple Watch — better |
| Requires iOS | 18.0 | 16.4 — better |
| Further details — not scored | ||
| Size | 29 MB | 45 MB |
| Age rating | 4+ | 17+ |
| Developer | 燚 张 | 子泰 陈 |
In-app purchases
Agent Lab
- Cola$0.99
- Coffee$1.99
- AgentLab Pro$2.99
Show 1 moreShow fewer
- A meal$3.99
AgentCmd
No in-app purchases









