Skip to content

Open Webui Plugins

A curated collection of Open WebUI plugins - tools, skills, filters, pipes, actions and events that extend your AI chat experience.

Install

$git clone https://github.com/Classic298/open-webui-plugins

Install command taken from the project's README or registry entry. Always review code before running it.

🧩 Open WebUI Plugins

A curated collection of plugins for Open WebUI: tools, skills, filters, pipes, actions and events that extend your AI chat experience.

Each plugin lives in its own folder with a README explaining what it does, what components it includes, and how to set it up.


Plugins

Plugin Description Components
Inline Visualizer 🔹 LIVE RENDERED 🔹 Your model draws interactive charts, dashboards, diagrams and mini-apps right in the chat, appearing live while the answer streams. Everything matches your light/dark theme automatically, and you can click a bar or a node and ask the model about it. Works with hand-written SVG/HTML and with Chart.js, D3, Vega-Lite, ECharts, Plotly, vis-network and Tone.js. Tool + Skill
Prune ⭐ NEW ⭐ Old chats, inactive users and orphaned files are cleaned out automatically in the background, so slowly that a live instance never notices. Dry-run by default, with an admin page at /prune to preview and run cleanups manually. Safe across replicas. Event
Interface Defaults Open WebUI's Default Interface Settings page cannot push your defaults onto existing users. This adds that, a full factory reset, and defaults for the settings that page cannot reach: notifications, keyboard shortcuts, memory, the personal system prompt and the speech/voice block. Event
Email Composer Draft emails with your model and get a real email card in the chat: edit the rich text, adjust To/CC/BCC and priority, then download it as .eml or hand it to your mail app with one click. Tool
MCP App Bridge Use MCP Apps (SEP-1865) inside your chat: connect an MCP server and its tools bring their own interactive interface, rendered as an embedded panel right where the model called them. No middleware and no core changes needed. Tool
Vision Bridge Lets a text-only model work with images: attach a picture, or let the model create one in Open Terminal, and it asks a separate vision model to look at it on demand, then comes back with new questions about the same image any time. No core changes. Filter + Tool
Better Banners ⭐ NEW ⭐ Your admin banners, in every chat: at the top of the page or right above the message input, collapsible, dismissible, updated live and shown in each user's language. Event

Shared Assets Protocol

Plugins that add JavaScript or CSS to every Open WebUI page can use the Shared Assets Protocol, a community standard that lets them all run side by side without overwriting each other.


Plugin Types

Similar plugs

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…

Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.

The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…