
Quercle Chat: Open Source AI Chat with Web Tools
TL;DR
Quercle Chat is an open source AI chat interface that runs entirely in your browser. No backend, no server storing your conversations - everything stays local. Use any OpenRouter model with persistent conversations, real-time streaming, and web capabilities powered by Quercle.
Links:
What is Quercle Chat?
Quercle Chat is a fully client-side AI chat interface built with Next.js. Unlike proprietary chat services that store your data on their servers, Quercle Chat runs entirely in your browser - your API keys, conversations, and settings never leave your machine.
Use any model available on OpenRouter - from GPT-4 to Claude to open source models like Llama and Mistral.
Key Features
- 100% Client-Side - Runs entirely in your browser, no backend server
- Your Data Stays Local - API keys, conversations, and settings stored in your browser only
- Model Flexibility - Connect to any OpenRouter model with a single API key
- Persistent Conversations - All chats saved locally using IndexedDB (Dexie.js)
- Real-time Streaming - Watch responses stream in as they're generated
- Tool Calling Visualization - See AI agent tool usage with detailed cards
- Thinking Process Display - Collapsible reasoning blocks show the AI's thought process
- Web Capabilities - Built-in web search and fetch tools powered by Quercle
- Dark Mode UI - Beautiful dark theme with Tailwind CSS
- Mobile Responsive - Works seamlessly on desktop and mobile
Tech Stack
| Component | Technology |
|---|---|
| Framework | Next.js (App Router) |
| Runtime | Bun |
| Styling | Tailwind CSS 4 |
| UI Components | Radix UI + shadcn/ui |
| Database | IndexedDB (Dexie.js) |
| AI SDK | @quercle/ai-sdk, @openrouter/ai-sdk-provider |
Getting Started
Head to chat.quercle.dev and start chatting:
- Click the settings icon in the header
- Enter your OpenRouter API key (for AI models)
- Enter your Quercle API key (for web search and fetch tools)
- Select a model
- Start chatting!
All settings are stored locally in your browser - no server-side storage needed.
Web Tools Integration
Quercle Chat comes with built-in web search and fetch tools powered by Quercle. The AI can:
- Search the web and synthesize answers with citations
- Fetch and analyze web pages with custom prompts
- Research topics across multiple sources
This makes it ideal for research, fact-checking, and staying up-to-date on current events.
Why Open Source?
We built Quercle Chat to demonstrate what's possible with Quercle's web tools and the AI SDK. By open sourcing it, we hope to:
- Provide a reference implementation for developers building AI chat interfaces
- Show how to integrate web search and fetch capabilities into chat applications
- Give users more control over their data - your API keys and conversation history stay in your browser, not on a third-party chat service's servers (though conversations are still sent to OpenRouter and model providers)
Contributions are welcome! Feel free to submit PRs for new features or improvements.
Try It Now
- Start chatting: chat.quercle.dev
- Source Code: github.com/LiranYoffe/quercle-chat
Ready to try Quercle?
Built for AI agents. See how it compares in real-world tests.
More Articles

Building an AI Research Agent with Persistent Memory
Learn how Quercle Research Agent remembers what it learns across sessions. An open source AI assistant that builds knowledge over time using Quercle, MongoDB, and OpenRouter.

SERP MCP: Local Google Search for AI Agents
Get Google search results locally with SERP MCP - an open source MCP server with fingerprint rotation. Learn when to use it vs Quercle for your AI agents.

Quercle + xpander.ai: Powering AI Agents with Web Data
Quercle integrates with xpander.ai to give AI agents reliable web access. See how to build agents that monitor GitHub trends, research topics, and more.

Testing LLM Security: A Prompt Injection Testing Ground
Sunny Valley Farm is not what it seems. An open source website for testing whether LLM web tools can defend against prompt injection attacks.

How Claude Code Web Tools Work: WebFetch and WebSearch Internals
A deep dive into how Claude Code implements WebFetch and WebSearch tools internally. Learn about secondary conversations, Haiku processing, and how to build better alternatives.

Quercle vs Tavily: Which Web API is Best for AI Agents?
A detailed comparison of Quercle and Tavily for AI agent web access. Compare features, pricing, security, and when to use each.

Quercle vs Exa: Choosing the Right Web API for Your AI Agents
Compare Quercle and Exa for AI-powered web access. Learn about their differences in search, content extraction, and agent integration.

Quercle vs Firecrawl: Web Scraping APIs for AI Agents Compared
Compare Quercle and Firecrawl as web fetching APIs for AI agents. See how they differ in security, pricing, and developer experience.