
Kelivo is a free, open-source LLM chat client for people who want to use local and cloud models in the same app while keeping their conversation history on their own device. It connects to Ollama, self-hosted OpenAI-compatible endpoints, and providers such as OpenAI, Gemini, Claude, DeepSeek and OpenRouter. The app runs on Android, iOS, HarmonyOS, Windows, macOS and Linux, including Apple Silicon and Intel Macs.
Kelivo stores conversations, settings and files locally and doesn't require an account of its own. Model requests go to the backend you choose, so local storage doesn't make a cloud conversation private to your device. You can use your own provider API keys or sign in through supported accounts. Optional backups go to WebDAV or S3-compatible storage under your control.
Custom assistants let you keep separate models, prompts and tools for different tasks. Long-term memory can apply across assistants or stay within one, and you can inspect and edit what it remembers. Keyword-triggered context entries add relevant background to a conversation. Chat branches and response versions let you explore different answers without losing the original thread, while temporary chats aren't saved.
For work that needs outside information, Kelivo supports PDF reading, web search and MCP tool connections. Search choices include DuckDuckGo, Brave, SearXNG, Exa and Tavily, and search answers include source citations. Provider configurations can be shared by QR code. Kelivo is built with Flutter and licensed under AGPL-3.0.
Claim this page with an email at kelivo.psycheas.top. Kelivo 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 Kelivo?Promote it
Something wrong or outdated on this page?
66.6KUpdated 14 hours agoMIT
macOS · Windows · Linux · Android · Docker · Web#LM Studio integration#MCP#Multimodal input
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.
827Updated 9 months ago
macOS · Windows · Linux · Docker#GGUF#Human approval#MCP
ARGO is a local AI agent platform for people who want assistants that can research a topic, work with their documents and carry out tasks with several steps. It runs on Windows, macOS and Linux, including Intel and Apple Silicon Macs, or through Docker. You can create specialized assistants by describing their role in plain language.
3.2KUpdated 5 days agoMIT
macOS · Windows · Linux · iOS · Android#GGUF#Human approval#LM Studio integration
noemaai.comChat With Your Documents
macOS · iOS#GGUF#MCP#MLX
3.3KUpdated 1 day agoMIT
macOS#GGUF#llama.cpp backend#OpenAI-compatible API
141Updated 21 hours ago
macOS · Windows · Linux · iOS · Web#Agent Skills#Code execution#Human approval
Bloks is a desktop workspace for people who want personal AI agents on their own computer, with conversations arranged like a messaging app. Agents appear as contacts, and shared rooms let them work together. It runs on macOS, Windows and Linux. The desktop app needs no Bloks account and is source-available under FSL-1.1-MIT.
Off Grid AI runs language models on iOS, Android, macOS, Windows and Linux. You can chat, analyze documents and generate images on your own hardware. The mobile app uses the MIT license, while the desktop app uses AGPL.
Noema is a private local AI assistant for iPhone, iPad, Mac, and Vision Pro. It's for people who want to chat with models and work with their own files on Apple hardware without depending on a cloud service. Local chats can stay on your device, and file retrieval runs there too.
Sidekick is a native macOS app for people who want AI chat grounded in their own documents and research materials. Its built-in llama.cpp engine runs GGUF models such as Qwen3.5 without separate model software. Local conversations work offline. The app is open source under the MIT license and requires an Apple Silicon Mac with at least 8 GB of RAM.