Uses Flask to provide a Web UI service with HTTP API endpoints for real-time user intervention and feedback management during AI agent interactions.
Renders Markdown content in the Web UI for displaying agent messages and user feedback with code highlighting and math rendering support.
Uses Mermaid for architecture diagrams in documentation to visualize the system's component relationships and data flow.
When using AI CLIs/IDEs, agents can drift from your intent. This project gives you a simple way to intervene at key moments, review context in a Web UI, and send your latest instructions via interactive_feedback so the agent can continue on track.
Works with Cursor, VS Code, Claude Code, Augment, Windsurf, Trae, and more.
Quick start
Install:
Configure your AI tool to launch the MCP server via
uvx:
>interactive_feedback is a long-running tool. Some clients have a hard request timeout, so the Web UI provides a countdown + auto re-submit option to keep sessions alive.
Screenshots
Key features
Real-time intervention: the agent pauses and waits for your input via
interactive_feedbackWeb UI: Markdown, code highlighting, and math rendering
Multi-task: tab switching with independent countdown timers
Auto re-submit: keep sessions alive by auto-submitting at timeout
Notifications: web / sound / system / Bark
SSH-friendly: great with port forwarding
VS Code extension (optional)
Item | Value |
Purpose | Embed the interaction panel into VS Code’s sidebar to avoid switching to a browser. |
Install (Open VSX) | |
Download VSIX (GitHub Release) | |
Setting |
|
Configuration
Item | Value |
Docs (English) | |
Docs (简体中文) | |
Default template |
|
OS | User config directory |
Linux |
|
macOS |
|
Windows |
|
Architecture
Documentation
API docs index:
docs/api/index.mdAPI docs (简体中文):
docs/api.zh-CN/index.md
Related projects
License
MIT License