Task-oriented AI Agent productivity platform — redefining operational boundaries and memory evolution, one WorkSpace at a time.
English | 简体中文
Website · Live Demo · Tutorial · Quick Start · Highlights · Use Cases · Community
News 🔥
- [2026.05.28] PilotDeck is now open source! Visit our official website at pilotdeck.openbmb.cn. We welcome contributions, feedback, and stars from the community.
PilotDeck is an open-source agent operating system designed around the concept of "WorkSpace". It is jointly developed and open-sourced by Tsinghua University THUNLP, ModelBest, OpenBMB, and AI9Stars. Targeting general-purpose, multi-task scenarios, PilotDeck is built to be a true productivity tool for the Agent era.
A wave of excellent AI Agent harnesses has emerged in recent years, each with its own focus: Claude Code / Cursor / Trae Solo brought model reasoning deep into the programming IDE; Claude Cowork introduced the notion of project-level isolation to desktop-side knowledge work; WorkBuddy connected agents to IM ecosystems such as WeCom and Feishu so AI is one message away.
When we shift the lens from "one-shot programming" or "immediate Q&A" to long-running, multi-project productivity work, however, several questions remain open:
- When many projects run in parallel, can memory be white-box and traceable? When the AI gets something wrong, can you pinpoint which memory entry caused it and edit it directly — without starting a new chat from scratch?
- Can token cost be tracked per task, so that running agents in the background actually becomes economically viable?
- Can tasks of different difficulty automatically be matched to different models, instead of burning the flagship model on trivial calls?
- When you step away from the keyboard, can the work keep moving? Can the agent proactively discover what's worth doing, report progress, and land results as files on disk?
PilotDeck is an incremental exploration around exactly these questions. It uses the WorkSpace as the fundamental unit — completely isolating files, memory and skills per project — and pairs it with three pillar capabilities: White-box Memory, Smart Routing and Always-on. The entire system natively supports the Model Context Protocol (MCP) and behaves consistently across front-ends (Web / CLI / IM).
|
WorkSpace-Level Isolation & Accretion Every project gets its own file system, memory store and skill set. Parallel work no longer interferes with itself, retrieval has a bounded scope, and skills accrete naturally as each task grows — no more global context pollution.
|
Traceable White-box Memory Memory generation, extraction, storage and retrieval are visible end-to-end. When the AI mis-remembers, you can pinpoint and fix the offending entry. Built-in Dream Mode consolidates memory in idle windows, and supports one-click rollback.
|
|
Smart Routing & Cost Optimization Task difficulty is auto-detected; complex calls go to flagship models (e.g. Claude 3.5 Sonnet / GPT-4o), simple ones drop to lighter models. Through on-device / cloud co-orchestration and precise matching, token spend shrinks dramatically without sacrificing quality.
|
Always-on Background Execution PilotDeck breaks the "you ask, it answers" loop: after you sign off, the agent keeps discovering candidate tasks, running long-horizon monitors, and finally lands deliverables as local files with a summary report waiting for you.
|
The three pillar capabilities have shown clear advantages in production-grade workflows:
In Xiaohongshu-style social-media operations, enabling Smart Routing automatically demotes simple polishing / layout tasks to a sub-agent (e.g. Sonnet 4.5) and only invokes Opus 4.5 at planning checkpoints:
| Setup | Model configuration | Cost | Multiplier |
|---|---|---|---|
| Smart Routing ON | Opus 4.5 (main) + Sonnet 4.5 (sub) | $2.83 | 1.1× |
| Smart Routing OFF | All Opus 4.5 (main + sub) | $12.58 | 5.0× |
| Monolithic | Single Opus 4.5 long-react (estimated) | $12.20 | 4.8× |
The research team benchmarked 7 complex tasks (multilingual podcast push, multi-source data reports, domain-specific literature review, codebase architecture docs, etc.). The "strong main + light sub" routing setup matches or beats the frontier single-model setup at a fraction of the cost:
| Setting | Score | Cost |
|---|---|---|
| MiniMax-M2.7 single-agent | 37.1 | $1.90 |
| Claude Sonnet 4.6 single-agent | 69.1 | $18.36 |
| Sonnet 4.6 (main) + MiniMax-M2.7 (sub) | 70.6 | $3.15 |
In black-box agents, mixing tasks in a shared context pool inevitably pollutes memory. PilotDeck's WorkSpace-scoped white-box memory addresses this end-to-end:
| Dimension | Current AI Agents (black-box) | PilotDeck (white-box) |
|---|---|---|
| Visibility | You can't see what the AI remembers, only what it outputs | View every memory entry: what was stored, when, and which WorkSpace |
| Control | Once written, memory can't be edited or removed | Edit / delete entries, pin critical decisions so they don't drift |
| Traceability | When it goes wrong, you can't find the root cause | Generation → extraction → storage → retrieval, all auditable |
| Isolation | One shared pool — projects bleed into each other | Scoped per WorkSpace; A's memory never reaches B |
| Reversible | After compression, the original is gone | Dream-mode supports one-click rollback to the prior state |
PilotDeck ships an out-of-the-box Web UI with full WorkSpace management, white-box memory editing, and visualization of multi-agent collaboration.
All demos below are generated entirely by edge-side models via PilotDeck's Smart Routing — no cloud-side frontier model required.
"Survey the Chinese LLM application market and turn it into a formal HTML white paper."
| Process | Result |
 |
 |
"Walk me through building an iOS AR mini-game Ball Finder in Vibe Coding mode."
| Process | Result |
 |
 |
"Build a low-code embedding fine-tuning platform from scratch."
| Process | Result |
 |
 |
"Push this English podcast to a global audience in Chinese / Japanese / French / Korean / Spanish / Arabic."
| Process | Result (with audio) |
 |
podcast_result.mp4 |
We provide a one-line installer for macOS / Linux, plus a source-based workflow for developers.
curl -fsSL https://raw.githubusercontent.com/OpenBMB/PilotDeck/main/install.sh | bashThe script auto-installs Node.js 22, clones the repo, installs dependencies, and builds the frontend. Once it finishes:
pilotdeck # starts the server at http://localhost:3001
pilotdeck status # check runtime status1. Clone and install dependencies
This repo uses Git LFS for large media assets. Make sure
git lfsis installed before cloning. If you don't need the demo videos/GIFs, addGIT_LFS_SKIP_SMUDGE=1beforegit cloneto skip downloading them.
git clone https://github.com/OpenBMB/PilotDeck.git
cd PilotDeck
npm install # root deps (Gateway runtime)
cd ui && npm install # UI deps
cd ..2. Configure a model provider
PilotDeck reads ~/.pilotdeck/pilotdeck.yaml. You can create it manually, let the bootstrap script generate one, or just open the Web UI and configure providers visually in the settings panel.
Supported protocols include OpenAI, Anthropic, DeepSeek, Qwen, Kimi, MiniMax and other OpenAI-compatible endpoints.
schemaVersion: 1
agent:
model: deepseek/deepseek-v4-pro
model:
providers:
deepseek:
protocol: openai
url: https://api.deepseek.com/v1
apiKey: sk-your-api-key3. Start the services
cd ui && npm run dev # dev mode (HMR), visit http://localhost:5173
# or
cd ui && npm run start # production mode, visit http://localhost:3001If Docker is installed, you can start PilotDeck with:
docker compose up -dFor macOS users we ship a signed, Apple-notarized DMG — double-click to run, no command-line setup required.
PilotDeck has an open plugin architecture with a strict boundary between the open-source core and plugin customization. Extending the system is a plugin.json away:
- MCP Servers — first-class integration with any Model Context Protocol server.
- Tools & Skills — register custom tools, or pull community skills via ClawHub.
- Lifecycle Hooks — intercept
PreToolUse,UserPromptSubmit, and other critical lifecycle events. - Custom Memory — plug in your own memory store provider.
Thanks to everyone who has contributed code, feedback, and ideas. New contributors are warmly welcome — let's build the next-gen agent OS together.
Workflow: Fork → feature branch → PR. Please make sure the unit tests and linters pass before opening a PR:
npm test
cd ui && npx vitest run- For bugs and feature requests, please open a GitHub Issue.
- Join our community channels:
| WeChat Community | Feishu Community | Discord Community |
 |
 |
 |
PilotDeck builds upon the following outstanding open-source projects:
- ClawXRouter — Intelligent model routing
- ClawXMemory — Agent memory system
- Claude Code UI — Web UI reference
- Claude Code Router — Model routing reference
- UltraRAG — RAG framework
- Anthropic Skills — Agent skill framework and built-in skills (skill-creator, frontend-slides)
- MiniMax-AI Skills — minimax-pdf skill
- Karpathy Guidelines — LLM coding behavioral guidelines
- Vite — Frontend build tool
- React — UI framework
- Tailwind CSS — Utility-first CSS framework
PilotDeck is jointly developed by Tsinghua University THUNLP, ModelBest, OpenBMB and AI9Stars.
If PilotDeck has been helpful in your work or research, please consider giving us a Star on GitHub!
@misc{pilotdeck2026,
author = {PilotDeck Team},
title = {PilotDeck: A WorkSpace-Centric Open-Source Agent Operating System},
howpublished = {\url{https://github.com/OpenBMB/PilotDeck}},
year = {2026},
note = {Accessed: 2026-05-29}
}This project is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0). The products/** directory contains customer-specific customizations and is not part of the open-source release scope.