TinyWebUI

TinyWebUI is a local-first chat workspace for OpenAI-compatible models that includes built-in Model Context Protocol tools.

TinyWebUI is a local-first chat workspace designed to connect with any OpenAI-compatible endpoint such as OpenRouter, OpenAI, Groq, Ollama, vLLM, or LM Studio. All chats, documents, and tool outputs are stored locally in a single SQLite file on your machine. It features built-in TinySuite MCP servers including TinySearch for local web searches and TinyContext for local long-term memory. Users can attach text files, PDFs, DOCX documents, and images to conversations. The platform supports advanced capabilities like steering active turns, hybrid local search using BM25 and on-device embeddings, cache-friendly prefixes, cron-scheduled automations, and optional SSO authentication for teams.

TinyWebUI at a glance

Best for: Software engineer
Runs on: Web, CLI, self-hosted, open source
Pricing: Free
Released: October 2026
Category: AI chat assistant
Website: github.com/tinysuitehq/tinywebui

Key features

Durable conversations with editing, retries, and full-text search
Turn steering to guide model output while running
MCP support over stdio, Streamable HTTP, or SSE
File attachments including text, PDFs, DOCX, and images
Hybrid local search using BM25 and on-device embeddings
Token statistics and cache-friendly prompt prefixes
Cron-scheduled prompt automations
Configurable password protection and team SSO support

Use it for

Chatting with local and cloud AI models via OpenAI-compatible endpoints
Searching and reading the web locally without an external search API key
Managing long-term memory across chat sessions with token budgets
Running scheduled prompt automations inside selected chats
Searching through past chats and attached documents using hybrid search

Companions

Tools that articles about TinyWebUI recommend using with it, each with its job.

Ollama — Run open models locally or in the cloud with private prompts
SearXNG — Built-in integration for web-grounded answers.
ComfyUI — Local image and video generation on a node canvas, with every model and parameter in reach
LiteLLM — Per-user keys and routing for clients outside the web UI.
Hermes Agent — Adds agentic workflows on the same local models.
Cloudflare Tunnel — Reach the homelab without opening ports.

Alternatives to TinyWebUI

Open WebUI — Run AI on your own terms with complete data privacy and self-hosting control.
Littleaibox — It keeps conversation state and parsed files locally on the device.
llmspy.org — Self-host access to 530+ AI models across 24 providers with built-in tools.
5ire — It supports local knowledge base management and Model Context Protocol servers.
Text Generation WebUI — Run local LLMs with multiple backends, multimodal input, and tool calling 100% offline.
Dot2api — Queues requests and wakes up your Dot to answer securely over MCP.
LibreChat — Unifies multiple AI models and tools in one customizable, open-source platform.
Kelivo — Connect to any model with local-first data storage and multi-platform support.
HuggingChat UI — It provides a customizable open source chat interface for any OpenAI-compatible backend.
RikkaHub — Integrates a Linux workspace for AI agents on Android devices.
Page Assist — Interact directly with local AI models on any webpage via a sidebar and web UI.
Uniichat — Maintains one unending chat with a memory tree that never loses historical detail.

All TinyWebUI alternatives