PandaNpc Work

Multi-engine AI workspace for research, creation, and coding

Hand work to AI and keep track of progress anytime. PandaNpc Work connects multiple Agents, including Claude Code and Codex, letting research, information organization, content creation, and coding tasks move forward in one workspace.

When your execution machine stays online, you can view progress, answer questions, and continue sessions from mobile, browser, or desktop.

Chat with Bot

My Agent Cloud

The Agent Cloud is your own cloud dev machine. Sign in to create and use it.

Claude CodeCodexPandaCodeDeepSeek harness (CLI)Pi

LIVE ROUTE/agent · guest modeOpen full page

Start with a task

Use AI to advance research, content creation, and coding

Choose the right Agent and entry point, and keep moving toward a clear outcome.

01Research

Research information and form usable conclusions

Let AI gather leads, organize information, and summarize key points; then you verify sources and decide next steps.

View practical examples

02Creation

From materials to content deliverables

Organize existing materials, draft articles, explanations, and plans, and save what is worth keeping into notes.

Learn about AI notes

03Coding

Advance code tasks in real projects

Connect to a running coding Agent, view the process, handle confirmations, and inspect code changes and results.

Open workspace

Multiple engines, one work surface

Choose the Agent you already use by task

PandaNpc Work brings sessions from multiple Agents together in one interface. You can switch engines and connections and see what each piece of work is doing.

Each engine keeps its own capabilities, account, and runtime environment; you can choose the right engine for the task and provide the needed context and feedback separately.

Claude Code

View sessions, tool calls, questions, and code changes.

Codex

Connect to Codex sessions, continue tasks, and inspect execution results.

PandaCode

Use configurable models to advance conversations and coding work.

DeepSeek harness (CLI)

Connect to DeepSeek harness (CLI) to view and continue current tasks.

Pi

Connect to Pi sessions and follow the task process.

Follow along across devices

Stay on top of Agent progress away from your computer

Execution still happens on the connected machine and in the session environment. When the machine stays powered on, the Agent process is online, and the network is available, you can continue to view and operate from other devices.

When a task needs confirmation, more information, or has produced results, open it on mobile, in the browser, or in the desktop app to return to the same session.

Return to the same Agent session from mobile, browser, or desktop while the execution environment is online.

Outputs you can keep using

Turn the process into project materials and notes

After a task is complete, organize conclusions, drafts, code notes, and follow-up items into project materials or notes so they are easy to edit, find, and share.

You can organize important context and outputs by project, making it easier to find what you need when you continue working next time.

PandaPaw

Remote access to every computer running your AI agents

Add PandaPaw to each agent host under the same PandaNpc account. The computers automatically join a private network, letting you continue Claude Code, Codex and PandaCode sessions from your phone, browser or another computer—without a public IP or port forwarding.

Device networking diagram: Agent computers with PandaPaw under the same account automatically join a private network, while phones and browsers access those hosts remotely.

Share a Claude Code connectionLearn how to hand a live connection to someone you trust without sharing account credentials.

FAQ

About PandaNpc Work

What is PandaNpc Work?

PandaNpc Work is a workspace that connects multiple AI Agent engines, used to view and continue research, information, content, and coding tasks.

Which Agents are supported?

The current work surface supports Claude Code, Codex, PandaCode, DeepSeek harness (CLI), and Pi. The specific capabilities of each engine depend on its version, account, and runtime environment.

Can I continue computer tasks from my phone?

Yes, but the execution machine must stay powered on, and the Agent process and network must be online. Mobile and browser are used to connect to, view, and continue that session.

How do I choose an Agent for a task?

You can choose an engine based on the task type, existing accounts, and runtime environment, and view tasks and provide feedback separately within the same work surface.

Where can task results be saved?

You can organize useful conclusions, drafts, and explanations into project materials or notes; code results remain in the corresponding project environment.