
Brave Leo is an AI assistant built into the Brave browser, with Bring Your Own Model support for people who want to use their own local or remote models while browsing. It can work with third-party APIs as well as Brave's hosted model choices. The browser runs on macOS, Windows, Linux, Android, and iOS.
The appeal is access to the material you're already reading. Leo can summarize webpages, analyze PDFs, and answer questions about Google Docs and Google Sheets without making you switch to a separate chat app. It also translates text, drafts articles and emails, and suggests code or database queries. For browsing tasks, it can find tabs related to a topic and gather them into a new window.
Where processing happens depends on the model you choose. BYOM lets you connect to models running locally or remotely; Brave's hosted service sends your prompt, conversation context, and relevant page content to the servers that answer it. Hosted choices include Mixtral, Anthropic's Claude, and Meta's Llama. Leo also uses Brave Search for answers that need current information.
Chat history stays on your device. You can revisit saved conversations, or use temporary chats that disappear when closed. Leo can remember preferences across chats, and Brave says it doesn't retain conversations on its servers or use them for model training.
No account is required for the basic Leo experience. Brave is an open-source browser licensed under Mozilla Public License 2.0. On iOS, Leo supports voice-to-text questions.
Claim this page with an email at brave.com. Brave Leo (Bring Your Own Model) 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 Brave Leo (Bring Your Own Model)?Promote it
Something wrong or outdated on this page?
46Updated 5 days agoAGPL-3.0
macOS · Windows · Linux · Browser Extension#Code execution#GGUF#llama.cpp backend
Vyact is an open source desktop workspace for people who want to use a local LLM with their documents, email and code. It runs on Apple Silicon Macs, Windows and Linux x64 under the AGPL-3.0 license. Intel Macs aren't supported.
1.1KUpdated 7 months agoAGPL-3.0
Web · Browser Extension#Multilingual#Multimodal input#Ollama integration
2KUpdated 6 months agoAGPL-3.0
macOS · Windows · Linux#Code execution#LM Studio integration#MCP
66.6KUpdated 2 hours agoMIT
macOS · Windows · Linux · Android · Docker · Web#LM Studio integration#MCP#Multimodal input
41.9KUpdated 6 days agoGPL-3.0
macOS · Windows · Linux · iOS · Android · Web#MCP#Multimodal input#Ollama integration
38.7KUpdated 11 months agoApache-2.0
macOS · Windows · Linux · Docker · Web#Multimodal input#Ollama integration#OpenAI-compatible API
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.
Witsy is an AGPL-3.0 desktop AI assistant for macOS, Windows and Linux that connects MCP tools to local and cloud models. It's for people who want document chat, writing help and voice features in one app, with a choice of where their models run.
AnythingLLM is an open source AI assistant for people who want to chat with their documents and use AI agents on their own hardware. The desktop app runs on Windows, macOS and Linux, while a Docker deployment supports multiple users on a self-hosted server. No account is required for the desktop app.
Chatbox is an AI chat client for people who want local models and cloud providers in the same app. It connects to Ollama for local LLM use and supports GPT, Claude, Gemini, Grok and DeepSeek with your own API keys. Chatbox also offers its own hosted model service.
Langchain-Chatchat is a self-hosted application for asking questions about your own documents and using AI agents. It focuses on Chinese-language use and open models, with a fully offline setup that can keep documents and model processing on your hardware. Its code is open source under Apache 2.0.