I built PinchChat, an open-source webchat UI for OpenClaw

Source: Dev.to

Overview

I’ve been running OpenClaw as my personal AI assistant for a while, and the default terminal/CLI interface wasn’t cutting it for everyday use. So I built PinchChat, a lightweight, self‑hosted web‑chat UI designed specifically for OpenClaw.
It provides a ChatGPT‑like interface for your own agent.

Features

• Live tool‑call visualization – see what your agent is doing in real‑time (file reads, web searches, code execution) with colored badges and expandable details.
• Multi‑session management – a sidebar shows all active sessions (cron jobs, sub‑agents, DMs from different channels).
• Token usage tracking – real‑time progress bars per session so you know how much context is left.
• Streaming – watch the agent think and type live, token by token.
• Inline images – generated or read images render directly in the chat with lightbox preview.
• Context compaction button – manually trigger compaction when token usage gets high.
• i18n – supports 8 languages (EN, FR, ES, DE, JA, PT, ZH, IT).
• PWA installable – works as a standalone app on mobile and desktop.
• Theming – multiple color themes and full dark mode (Dark, Light, OLED Black).
• Slash‑command autocomplete – quick access to OpenClaw commands.
• Conversation export – download chats as Markdown.
• Session info popover – token breakdown and metadata at a glance.

Stack

• Frontend: React + Vite + Tailwind CSS
• Deployment: Docker image available on ghcr.io; one‑command deploy.

Try it

Badges

Demo

PinchChat is MIT licensed, PRs are welcome. I’d love feedback from other OpenClaw users—what features would you like to see in a web‑chat UI?