SwiftQuantum vs Agent Lab

Design a quantum circuit, run it on your own device and watch every qubit — on iPhone, iPad and Mac. SwiftQuantum is a quantum circuit IDE for learners, students, educators and developers. Drag gates onto the canvas, tap Run and see the result as a Bloch sphere, a histogram and a state vector. Then take any circuit to Python as a Qiskit script, on every plan. RUN IT ON YOUR DEVICE • Free: circuits up to 10 qubits • Scholar: any circuit up to 25 qubits • Master and Enterprise: Clifford circuits up to 127 qubits, even offline • Circuits with non-Clifford gates run up to 25 qubits. Larger ones aren't simulated anywhere: the app tells you what to change and sends nothing • A circuit leaves your device only after you tap Send BUILD CIRCUITS YOUR WAY • Drag-and-drop editor with ready-made circuits such as Bell and GHZ states • Every gate is free: H, X, Y, Z, S, T, RX, RY, RZ, CNOT, CZ, SWAP, Toffoli and Fredkin • Three engines — Standard (Free), Turbo (Scholar) and HyperCore (Master) — each computes exactly the circuit you drew, in shot mode too • Export (OpenQASM, Qiskit), on every plan: OpenQASM 2.0 and a Qiskit Python script that runs as is with Qiskit 1.x (pip install qiskit); every qubit is measured at the end. OpenQASM 2.0 import too • Larger text and VoiceOver support on the circuit editor and the subscription screen SEE WHAT YOUR QUBITS DO • A Bloch sphere for each qubit, plus a measurement histogram and the state vector for every run • Export results: PNG and CSV on Scholar; LaTeX, PDF and SVG on Master • Paid plans: view the unitary matrix of small circuits; Master also compares gate fidelity ERROR-CORRECTION LAB (MASTER AND ENTERPRISE) • Surface-code experiments: choose the code distance, physical error rate and decoder • Logical error rate with a 95% confidence interval, computed on our servers (network needed) • Every curve says where it came from: our servers, your device (distance 3, offline) or a dashed reference formula AI THAT STAYS ON YOUR DEVICE • Optional: download a compact AI model once, describe a circuit in plain language and get a circuit back — generated without a network on supported devices • Your prompts stay on your device. Off by default; delete the model any time • Accepted results are sealed in a local, tamper-evident record: proof of where a circuit was made, not that it is correct NUMBERS YOU CAN CHECK • Benchmark (signed in): median run time per engine with a 95% confidence interval, measured on your device • Master and Enterprise: convert circuits to PennyLane and CUDA-Q code; each conversion shows its measured state overlap with your circuit, or "Not verified" • Q-Footprints: an opt-in log of your on-device runs that records only the shape of each run, never the circuit. Not a score or a certificate PLANS — FREE TO START • Free: 10 qubits, 10 simulations a day when signed in, 5 saved circuits • Scholar: 25 qubits, 100 simulations a day, 50 saved circuits • Master: Clifford circuits up to 127 qubits, 2,000 simulations a day, 1,000 saved circuits • Enterprise: contact us All results are classical simulations; SwiftQuantum does not run circuits on quantum hardware. — SwiftQuantum is free to download with optional auto-renewable subscriptions. Payment is charged to your Apple ID at confirmation of purchase and renews automatically unless cancelled at least 24 hours before the end of the current period. Manage or cancel anytime in your App Store account settings. Prices are shown in-app. SwiftQuantum is an independent tool for education and research and is not affiliated with or endorsed by any quantum hardware vendor. Qiskit is a trademark of IBM; SwiftQuantum is not affiliated with IBM. Terms of Use: https://legal.swiftquantum.tech/en/terms/ Privacy Policy: https://legal.swiftquantum.tech/en/privacy/

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.