
ThunderAI brings AI writing and email processing into Thunderbird for people who want help with their inbox while choosing where their messages go. It can use local models through Ollama or an OpenAI-compatible server such as LM Studio. Cloud connections send the selected content to ChatGPT, the OpenAI API, Google Gemini or Claude instead.
It drafts replies, corrects spelling and grammar, rewrites text in a chosen tone, and translates or summarizes messages. Proofreading includes a side-by-side change picker, so you can accept individual suggestions or edit them yourself. Rewrites preserve HTML formatting, and summaries can cover several emails at once.
For inbox organization, ThunderAI can suggest and assign Thunderbird tags or classify messages using your own criteria. API integrations also support automatic tagging, spam filtering, summaries and inline translations for incoming mail. These automatic actions skip drafts, templates, outbox and sent messages.
Custom prompts let you adapt the assistant to your own correspondence. You can share prompts through import and export, add reusable data placeholders, and choose a different provider or model for each prompt. Batch processing applies a prompt to multiple emails. The companion ThunderAI Sparks add-on lets it extract calendar events and tasks, including dates and descriptions.
ThunderAI is open source under GPL-3.0. Ollama processing runs fully locally and doesn't need an API key. The ChatGPT web connection requires an account but no API key; the OpenAI, Gemini and Claude API connections require keys.
Claim this page with an email at micz.it. ThunderAI gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find ThunderAI?Promote it
Something wrong or outdated on this page?
10.8KUpdated 2 days agoMIT
Browser Extension#Multilingual#Ollama integration#OpenAI-compatible API
ChatGPTBox is a free, open-source browser extension for people who want AI help with the pages they read, search results and selected text. It works in Chrome, Edge, Firefox and Safari, with mobile support too. You can connect it to Ollama or a self-hosted model through its custom model mode, or use cloud services such as ChatGPT, Claude, Moonshot and Azure.
181Updated 7 months ago
macOS · Windows · Linux#Multilingual#Ollama integration#OpenAI-compatible API
1.1KUpdated 7 months agoAGPL-3.0
Web · Browser Extension#Multilingual#Multimodal input#Ollama integration
253Updated 4 weeks agoMIT
macOS · Windows#MCP#Multilingual#Multimodal input
12.4KUpdated 22 hours ago
iOS · Android · Docker · Web#Batch processing
Inbox Zero is an AI email assistant you can self-host with Docker or use as a hosted service. It's for people handling busy Gmail, Google Workspace, or Microsoft Outlook inboxes who want help sorting mail and preparing replies. It works alongside your existing email client.
91Updated 1 day agoAGPL-3.0
Web#Multi-user access#Multilingual#Multimodal input
LocalWriter brings local LLM writing assistance into LibreOffice Writer for people who want to draft and revise text inside their documents. It runs on macOS, Windows and Linux and connects to a separate model runner, including Ollama and text-generation-webui. With a backend on your own machine, text processing stays local.
NativeMind brings a local AI assistant into Chrome for people who want help with webpages, documents, and writing without sending that content to a cloud model. The browser extension connects to Ollama on your machine, keeping prompts and AI processing on-device. It requires no account and uses the AGPL-3.0 open-source license.
Raycast Ollama brings Ollama models into Raycast on macOS and Windows, for people who want AI chat and text assistance within their desktop launcher. It connects to Ollama on your own machine or a remote server you choose. The extension is open source under the MIT license, and local inference doesn't require an Ollama API key.
Nextcloud Assistant brings AI into Nextcloud Hub's documents, email, chat and calendar. It's for teams that want help with shared work while choosing where AI processing happens. With an on-premises model, data stays on your server. The app is open source under AGPL-3.0.