ollama-client

🧠 Ollama Client — Chat with Local LLMs in Your Browser

Ollama Client is a powerful, privacy-first Chrome extension that lets you chat with locally hosted LLMs using Ollama — no cloud, no tracking. It’s lightweight, open source, and designed for fast, offline-friendly AI conversations.

---

---

✅ Works with any Chromium-based browser: Chrome, Brave, Edge, Opera, Chromium, and Arc.
🦊 Firefox support available via temporary addon installation (manual permissions setup required).

---

🚀 Get Started — Install Now

---

❤️ Upvote Us on Product Hunt!

🌐 Explore More

---

✨ Features

• 🔌 Local Ollama Integration – Connect to a local Ollama server (no API keys)
• 💬 In-Browser Chat UI – Lightweight, minimal, fast
• ⚙️ Custom Settings – Control model parameters, themes, prompt templates
• 🔄 Model Switcher – Switch between models in real time

• 🔍 Model Search & Pull – Pull models directly in the UI (with progress indicator)

• 🗑️ Model Deletion with Confirmation – Clean up unused models from the UI
• 🧳 Load/Unload Models – Manage Ollama memory footprint efficiently

• 📦 Model Version Display – View and compare model versions easily

• 🎛️ Tune Parameters – Temperature, top_k, top_p, repeat penalty, stop sequences
• 🧠 Transcript & Page Summarization – Works with YouTube, Udemy, Coursera & web articles
• 🔊 TTS – Built-in Text-to-Speech via Web Speech API
• 🗂️ Multi-Chat Sessions – Save/load/delete local chats
• 🧯 Declarative Net Request (DNR) – Automatic CORS handling
• 🛡️ 100% Local and Private – All storage and inference happen on your device
• 📋 Copy & Regenerate – Quickly rerun or copy AI responses

---

🧩 Tech Stack

• TypeScript
• React + Vite
• Plasmo (for Chrome extension boilerplate)
• Shadcn UI
• Ollama (local LLM backend)
• Chrome Extension APIs (declarativeNetRequest, storage, sidePanel)

---

🛠️ Quick Setup

✅ 1. Install the Extension

👉 Chrome Web Store

✅ 2. Install Ollama on Your Machine

brew install ollama  # macOS
ollama serve         # starts at http://localhost:11434

More info: https://ollama.com

✅ 3. Pull a Model

ollama pull gemma3:1b

Other options: mistral, llama3:8b, codellama, etc.

⚙️ 4. Configure the Extension

• Click the Ollama Client icon
• Open ⚙️ Settings

• Set your:

  • Local base URL: http://localhost:11434
  • Default model (e.g. gemma:2b)
  • Theme & appearance
  • Model parameters
  • Prompt templates

Advanced parameters like system prompts and stop sequences are available per model.

---

🛠️ Local Development Setup

Want to contribute or customize? You can run and modify the Ollama Client extension locally using Plasmo.

⚙️ Prerequisites

• Node.js (v18 or newer recommended)
• pnpm (recommended) or npm
• Ollama installed locally

---

📦 1. Clone the Repo

git clone https://github.com/Shishir435/ollama-client.git
cd ollama-client

---

📥 2. Install Dependencies

Using pnpm (recommended):

pnpm install

Or with npm:

npm install

---

🧪 3. Run the Extension (Dev Mode)

Start development mode with hot reload:

pnpm dev

Or with npm:

npm run dev

This launches the Plasmo dev server and gives instructions for loading the unpacked extension in Chrome:

• Open chrome://extensions
• Enable Developer mode
• Click Load unpacked
• Select the dist/ folder generated by Plasmo

---

🧪 4. Run in Firefox (Experimental)

pnpm dev --target=firefox

Load as a temporary extension.

---

🛠 5. Build for Production

pnpm build

Output will be in the build/ or dist/ folder depending on your Plasmo version.

---

📁 Code Structure

• src/: Core logic and components
• background.ts: API bridge + streaming
• sidepanel.tsx: Main chat UI
• options.tsx: Settings page
• content.ts: Summarizer / Readability
• lib/: Utility functions
• hooks/, features/, context/: Modular structure for maintainability

---

✅ Tips

• Change manifest settings in package.json
• PRs welcome! Check issues for open tasks

💡 Recommended Models by Device

System Specs	Suggested Models
💻 8GB RAM (no GPU)	gemma:2b, mistral:7b-q4
💻 16GB RAM (no GPU)	gemma:3b-q4, mistral
🎮 16GB+ with GPU (6GB VRAM)	llama3:8b-q4, gemma:3b
🔥 RTX 3090+ or Apple M3 Max	llama3:70b, mixtral

📦 Prefer quantized models (q4_0, q5_1, etc.) for better performance.

Explore: Ollama Model Library

---

🧪 Firefox Support (Experimental)

Ollama Client is a Chrome Manifest V3 extension. To use in Firefox:

1. Go to about:debugging
2. Click “Load Temporary Add-on”
3. Select the manifest.json from the extension folder
4. Manually allow CORS access (see setup guide)

---

🐛 Known Issues

• ⛔ “Stop Generation” doesn’t always abort early
• ⛔ “Stop Pull” during model download may glitch
• 🔒 CORS mostly handled via DNR, but can fail on older Chromium or network policies
• 💾 Large chat histories in IndexedDB may affect performance

---

🔮 Roadmap / Upcoming

• Chat search, filter, and export
• Improved error handling and offline UI fallback
• Better feedback for failed pulls or unreachable server

---

🔗 Useful Links

• 🌐 Install Extension: Chrome Web Store
• 📘 Docs & Landing Page: ollama-client
• 🐙 GitHub Repo: github.com/Shishir435/ollama-client
• 📖 Setup Guide: Ollama Setup Instructions
• 🐞 Issue Tracker: Report a Bug
• 🙋‍♂️ Portfolio: shishirchaurasiya.in
• 💡 Feature Requests: Email Me

---

📢 Spread the Word!

If you find Ollama Client helpful, please consider:

• ⭐ Starring the repo
• 📝 Leaving a review on the Chrome Web Store
• 💬 Sharing on socials (tag #OllamaClient)

Built with ❤️ by @Shishir435

This site is open source. Improve this page.