Self-Hosted Personal AI Assistants

Assistants like Khoj and Leon that remember what you told them, search your notes and files, and take on small tasks.

100+ tools
Favicon of QwenPaw

QwenPaw

1 video
A self-hosted AI assistant with persistent memory and chat app access, using local models through llama.cpp, Ollama or LM Studio.

37.7KUpdated 2 days agoApache-2.0

macOS · Windows · Linux · Docker · Web#Agent Skills#Human approval#llama.cpp backend

A local AI agent workspace for macOS, Windows and Linux that connects to Ollama or cloud engines and stores conversations on your computer.

316Updated 4 days ago

macOS · Windows · Linux · iOS · Web#Agent Skills#Code execution#Human approval

Favicon of Pieces

Pieces

1 video
An on-device AI memory tool that captures work across apps, stores memories locally by default, and shares context with MCP-compatible assistants.

pieces.appAgent Memory

#MCP#Persistent memory#RAG

A desktop AI agent for macOS, Windows and Linux that runs local file and command tools, with Claude, Codex and Gemini access and optional browser control.

2.3KUpdated 2 days agoMIT

macOS · Windows · Linux · Docker · Web#Agent Skills#Code execution#Git integration

Self-hosted AI assistant runs in Docker with local models through Ollama or LM Studio, or cloud providers. Free and open source under AGPL-3.0.

50Updated 1 day agoAGPL-3.0

Docker · Web#Agent Skills#Browser automation#Code execution

A local AI desktop app that gathers work notifications, researches context, and drafts actions using Ollama, LM Studio, or cloud models.

819Updated 2 days agoApache-2.0

macOS · Windows · Linux#Git integration#Human approval#Hybrid search

A desktop AI agent workspace for macOS and Windows that works with local files, schedules tasks and connects to cloud model providers.

593Updated 1 week agoAGPL-3.0

macOS · Windows#Agent Skills#Code execution#Git integration

A self-hosted AI agent that produces files on your Linux server, with isolated chat workspaces and support for Ollama or cloud models.

54Updated 4 days agoAGPL-3.0

Linux · Docker · Web#Agent Skills#Code execution#Human approval

A local AI voice assistant with a Portal-inspired voice, camera observations and persistent memory, using llama.cpp, Ollama or compatible cloud APIs.

5.8KUpdated 1 month agoMIT

macOS · Windows · Linux · Docker#Home Assistant integration#MCP#Multi-agent workflows

Favicon of OpenHuman

OpenHuman

7 videos
An open-source personal AI app with local model support, app integrations and multi-agent workflows, accessible through desktop, browser and terminal clients.

42.7KUpdated 20 hours agoGPL-3.0

macOS · Windows · Linux · Web#Human approval#LM Studio integration#MCP

A self-hosted AI agent supports Ollama and vLLM, optional semantic memory search, and chat through Telegram or WhatsApp.

324Updated 8 months agoMIT

macOS · Windows · Linux · Docker#Code execution#Guardrails#Hybrid search

Favicon of LogotyperLogotyper
Got an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.
Start your project
Favicon of Logotyper

More in Chat and Assistants