Stars
Forks
Watchers
Developer links
PilotDeck
PilotDeck introduces a WorkSpace-first architecture where each project receives its own isolated file system, memory store, and skill set, preventing context bleed between parallel tasks. White-box memory makes generation, extraction, storage, and retrieval fully visible, letting users audit, edit, pin, and rollback individual entries when the agent misremembers, while Dream Mode consolidates memory fragments during idle windows. Smart Routing auto-detects task difficulty and sends complex calls to flagship models like Claude Sonnet or GPT-4o while routing simple requests to lighter models, achieving claimed 70% cost savings through on-device and cloud co-orchestration with TokenSaver tiering and sticky session binding. Always-on background execution keeps agents running after the user closes the browser, with Discovery and Cron-based scheduling for recurring workflows. The platform natively supports the Model Context Protocol for first-class MCP server integration, community skills via ClawHub on npm, lifecycle hooks intercepting PreToolUse and UserPromptSubmit events, and custom memory store providers. Multi-provider fallback automatically switches to backup providers on timeout or rate-limit errors. The WebSocket and HTTP gateway serves web, CLI, desktop, and Feishu IM channels from a single configuration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.
Benefits
- Isolated WorkSpace Per Project
- Each project receives its own dedicated file system, memory store, and skill set with complete isolation, preventing context contamination between parallel agent tasks.
- Auditable White-Box Memory System
- Memory generation, storage, and retrieval are fully visible with audit, edit, pin, delete, and one-click rollback capabilities plus Dream Mode idle consolidation.
- Smart Routing Cost Optimization
- TokenSaver auto-classifies task difficulty and routes complex calls to flagship models while sending simple requests to lighter models, achieving up to 70% token cost savings.
- Always-On Background Execution
- Agents continue running after closing the browser with Discovery-based triggers and Cron-based scheduling for recurring workflows across all connected WorkSpaces.
Features
- Native MCP Integration
- First-class Model Context Protocol support for connecting MCP servers, community skills via ClawHub on npm, and lifecycle hooks for PreToolUse and UserPromptSubmit events.
- Multi-Provider Fallback
- Automatic failover to backup providers on timeout, rate-limit, or server errors with configurable fallback chains and zero-usage retry mechanisms.
- Multi-Frontend Gateway
- WebSocket and HTTP gateway serves web, CLI, desktop, and Feishu IM channels from a single configuration with consistent behavior across all frontends.
- Custom Router Extensions
- Plug in custom routing logic through router extension plugins, with scenario-based policies for default, explicit, and subagent model selection flows.
- Docker Compose Deployment
- One-command deployment with Docker Compose persisting full state including config, auth database, sessions, memory, skills, and router statistics.