page-agent/ROADMAP.md

🗺️ PageAgent Roadmap

The development progress and future plans for PageAgent.

🚀 Current Works

• MVP
  • Core functionality implemented.
• SPA interaction
• Reasoning and (short) memory
• Multi model provider integration and testing
• UI with HITL
  • Human-in-the-loop user interface. Agent can ask user questions.
• Landing and doc pages
• Remove ai-sdk
  • Only one function of AI-ADK is being used.
  • Our agent memory and thinking mechanism does not suite ai-sdk.
• Robust LLM output
  • Auto-fix incomplete output format of DeepSeek and QWen.
• Working homepage with live LLM API
• free CDN
• Free evaluation plan
• Custom actions and HITL
• Hooks and Events
  • lifecycle hooks
  • lifecycle events
• User takeover
• ❗Hijack page_open/page_change/page_unload behavior
• Custom knowledge base and instructions
• Black/white-list safeguard
• Data-masking
• Improve Memory
  • Current phrasing can cause logic-loop for some models.
  • Test adding Action to memory.
• Optimize for popular UI frameworks
• i18n of the website
  • Chinese version
  • English version
• Refactor: Separate Agent and PageController
• Chrome-ext wrapper

♻️ Following browser-use's update and contribute back.

📋 Pending Features

• Tools for more complex tasks
  • todo list
  • file sys
• Support custom llm fetch
• Testing suits
• Same-origin multi-page-app rally
• Local MCP proxy

🤔 To Be Decided

• Cross-origin multi-page?
  • Tricky
  • Need some kind of "memory rally"