Wordmark

Wordmark

An open source AI assistant platform

[](https://github.com/h1ddenpr0cess20/Wordmark) [](LICENSE) [](https://www.typescriptlang.org/)

[](https://github.com/h1ddenpr0cess20/Wordmark/stargazers) [](https://github.com/h1ddenpr0cess20/Wordmark/issues) [](https://github.com/h1ddenpr0cess20/Wordmark/pulls) [](https://github.com/h1ddenpr0cess20/Wordmark/commits)

Overview

Wordmark is a client-side AI chat for OpenAI/xAI Responses APIs and local LM Studio or Ollama servers. It supports tool/function calling, TTS, themes, and fully local storage — no backend required.

Screenshots

Desktop chat with streaming replies, a collapsible reasoning panel, and inline code — Aurora theme, running locally on google/gemma-4-12b-qat via LM Studio.

Configure everything from the settings panel — provider and model, tool calling, personality, and themes:

| Model | Tools | Theme | | :---: | :---: | :---: | | | | |

Fully responsive on mobile, with a range of built-in color schemes:

| Nebula | Ember | Forest | | :---: | :---: | :---: | | | | |

Docs:

• [Getting Started](docs/getting-started.md)
• [Overview](docs/overview.md)
• [Services & Models](docs/services.md)
• [Tool Calling](docs/tool-calling.md)
• [Skills](docs/skills.md)
• [Party Mode](docs/party-mode.md)
• [Streaming](docs/streaming.md)
• [Memory](docs/memory.md)
• [Security](docs/security.md)
• [Storage](docs/storage.md)
• [UI & UX](docs/ui-and-ux.md)
• [Docker](docs/docker.md)
• [Android App](docs/android.md)
• [Electron App](docs/electron.md)
• [Troubleshooting](docs/troubleshooting.md)

Features

• Providers — OpenAI Responses (hosted), xAI Grok (Responses-compatible), and local LM Studio or Ollama servers ([Services & Models](docs/services.md))
• Tool calling — built-in weather, provider web + X search, Code Interpreter, image generation, file search (OpenAI), direct file attachments (xAI), and custom MCP servers ([Tool Calling](docs/tool-calling.md))
• Documents — attach files or folders in any text/code format plus PDF, Office, OpenDocument, and ebooks; local providers extract and search them in-browser with embeddings, so nothing leaves your machine ([Documents & Attachments](docs/documents.md))
• Skills — uploadable SKILL.md instruction packages the assistant loads on demand to specialize for a task; ships with example skills ([Skills](docs/skills.md))
• Streaming & reasoning — dedicated reasoning panel, rich tool timelines, inline code previews, automatic image capture ([Streaming](docs/streaming.md))
• Party mode — autonomous multi-character group chat over your chosen provider; build a cast and scenario, then interject any time without pausing ([Party Mode](docs/party-mode.md))
• TTS — OpenAI (13 voices) and xAI (5 voices) providers, optional autoplay, per-message controls, audio cached locally
• UX — themes, responsive layout, syntax highlighting, markdown, image gallery ([UI & UX](docs/ui-and-ux.md))
• Local-only storage — conversations, images, and audio via IndexedDB; keys stay in the browser ([Storage](docs/storage.md))
• Memory — local, FIFO-limited memories appended to the system prompt ([Memory](docs/memory.md))

Quick Start

git clone https://github.com/h1ddenpr0cess20/Wordmark.git
cd Wordmark
npm install
npm run dev          # dev server on http://localhost:3000
# npm run dev:https  # HTTPS — needed for some APIs, TTS, and geolocation

Wordmark builds with Vite. Use npm run dev for development or npm run build to produce a static bundle in dist/ (serve it with npm run preview). Opening index.html straight from the filesystem no longer works — the app must be served by the dev server or built first. See [Getting Started](docs/getting-started.md).

1. In Settings → API Keys, add your OpenAI/xAI keys. Keys and URLs are stored locally.
2. Choose a provider and model in Settings → Model.
3. Type a message and send.

Local Models

• LM Studio — run the server (default http://localhost:1234), set the base URL in Settings → API Keys, then select LM Studio in Settings → Model ([LM Studio guide](docs/lm-studio.md))
• Ollama — run the server (default http://localhost:11434), set the base URL in Settings → API Keys, then select Ollama in Settings → Model

> Note: Chrome may prompt you to allow local network access. This is only used to connect to local LM Studio/Ollama servers.

HTTPS & Docker

HTTPS is recommended for full functionality — quick steps in [Getting Started](docs/getting-started.md). Full Docker/Compose instructions and SSL options in the [Docker guide](docs/docker.md).

# Pull from Docker Hub and run
docker run --rm -p 8080:80 h1ddenpr0cess20/wordmark:latest

Or build from source:

docker build -t wordmark:latest .
docker run --rm -p 8080:80 wordmark:latest

Architecture & Development

• [Architecture](docs/architecture.md) — high-level structure
• [Security](docs/security.md) & [Storage](docs/storage.md) — data handling
• [UI & UX](docs/ui-and-ux.md) — layout and design
• [Development](docs/development.md) & [CONTRIBUTING](CONTRIBUTING.md) — developer guide

Common tasks:

• Add tools — register tool metadata in src/ts/services/api/staticTools.ts, implement handlers (see src/ts/services/weather.ts), and tune provider quirks in src/ts/services/providers.ts — [Tool Calling](docs/tool-calling.md)
• Adjust models/providers — edit src/config/config.ts — [Services & Models](docs/services.md)
• Themes and styling — src/css/themes/**, src/css/components/**

Usage

• Enable Tools in Settings to allow function calls for weather, web search, file attachments, and any MCP servers you connect ([Tool Calling](docs/tool-calling.md))
• Manage conversations, images, and audio locally via History and Gallery
• Use TTS for spoken responses — configure provider and voice in Settings → TTS

Policies & Notes

• Privacy/Security — client-side only; no tracking ([Security](docs/security.md))
• Troubleshooting — common issues and tips ([Troubleshooting](docs/troubleshooting.md))
• Not a Companion — philosophy and boundaries ([Not a Companion](docs/not-a-companion.md))

License

MIT — see LICENSE

---

© 2025 Dustin Whyte | Released under the MIT License

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: h1ddenpr0cess20
• Source: h1ddenpr0cess20/wordmark
• License: MIT
• Homepage: https://wordmark-chatbot.vercel.app

Install and usage instructions live in the source repository linked above.