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

Nicolas Varrot — Sun, 15 Feb 2026 01:07:45 +0000

I've been running OpenClaw as my personal AI assistant for a while now, and the default terminal/CLI interface wasn't cutting it for everyday use. So I built PinchChat, a lightweight, self-hosted webchat UI designed specifically for OpenClaw.

It's basically a ChatGPT-like interface but for your own agent.

Features

Live tool call visualization so you can see what your agent is doing in real-time (file reads, web searches, code execution) with colored badges and expandable details
Multi-session management with a sidebar showing all active sessions (crons, sub-agents, DMs from different channels)
Token usage tracking with real-time progress bars per session so you know how much context is left
Streaming to watch the agent think and type live
Inline images that render directly in the chat
Context compaction button to manually trigger compaction when tokens run high
i18n with 8 languages (EN, FR, ES, DE, JA, PT, ZH, IT)
PWA installable so it works as a standalone app on mobile and desktop
Theming with multiple color themes and full dark mode
Slash command autocomplete for quick access to OpenClaw commands
Conversation export as Markdown
Session info popover with token breakdown and metadata

Stack

React + Vite + Tailwind. Docker image available on ghcr.io. One command deploy.

Try it

MarlBurroW / pinchchat

A sleek, dark-themed webchat UI for OpenClaw 🦞

PinchChat

A sleek, dark-themed webchat UI for OpenClaw — monitor sessions, stream responses, and inspect tool calls in real-time.

✨ Features

🔧 Tool call visualization — see what your agent is doing in real-time: colored badges, visible parameters, expandable results. The killer feature missing from every other chat UI.
💬 GPT-like interface — sessions in a sidebar, switch between conversations. Familiar if you've used ChatGPT or Claude.
📋 Multi-session navigation — browse all active sessions including cron jobs, sub-agents, and background tasks
⚡ Live streaming — watch the agent think and write token by token
📊 Token usage tracking — progress bars per session so you know how much context is left
🖼️ Inline images — generated or read images render directly in chat with lightbox preview
🎯 Chat-focused — no settings menus or config panels cluttering the screen. Just the conversation.
🎨 Themes — Dark, Light, and OLED Black…

View on GitHub

It's MIT licensed, PRs welcome. Would love feedback from other OpenClaw users. What features would you want in a webchat UI?

DEV Community: Nicolas Varrot