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 Inbox Zero

Inbox Zero

2 videos
An AI email assistant that sorts Gmail and Outlook and drafts replies in your voice, with hosted and Docker self-hosted options.

13KUpdated 23 hours ago

iOS · Android · Docker · Web#Batch processing

A self-hosted AI assistant uses Ollama or cloud models to search documents and automate tasks, with native apps for Windows, macOS and Linux.

5.7KUpdated 1 week agoApache-2.0

macOS · Windows · Linux · Web#Code execution#MCP#Ollama integration

A self-hosted AI assistant that edits local files, remembers context across chats and connects to Ollama or cloud models.

2Updated 23 hours agoMIT

macOS · Windows · Linux · Docker · Web#Code execution#MCP#Multi-agent workflows

A self-hosted AI agent for research, coding and system tasks. Works with local LLMs or cloud APIs on Ubuntu, macOS and Windows through Docker or WSL.

1.4KUpdated 1 year agoMIT

macOS · Windows · Linux · Docker · Web#Browser automation#Code execution#Human approval

A desktop AI agent works with project files through a connected model, with reusable workflows, scheduled tasks and MIT-licensed source code.

161Updated 3 weeks agoMIT

Windows#Agent Skills#Code execution#MCP

A self-hosted AI assistant for multiple users on Linux, with local models through Ollama or LM Studio and cloud providers including Claude and OpenAI.

14Updated 2 days agoAGPL-3.0

macOS · Linux · Web#Agent Skills#Home Assistant integration#LM Studio integration

A Windows AI agent app that coordinates custom agents, uses local models through Ollama, and keeps its database on your device.

nurgo-software.comAI Workflow Automation

Windows#Code execution#Multi-agent workflows#Multimodal input

A native Hermes AI agent client for macOS and iOS that manages chats, projects and local or remote hosts over SSH without an account.

915Updated 5 days agoMIT

macOS · iOS#Agent Client Protocol#Agent Skills#Human approval

An Android AI agent handles phone tasks and Solana trading through Telegram or Discord, using Claude, OpenAI, OpenRouter or a compatible gateway.

321Updated 2 weeks agoMIT

Android#Agent Skills#Human approval#MCP

A self-hosted personal AI agent with scheduled workflows, Telegram and Discord messaging, and local model support through Ollama and LM Studio.

119Updated 1 month ago

Docker · Web#Guardrails#Human approval#Hybrid search

A self-hosted AI assistant that runs in Docker, connects to email and calendars, and uses local models through Ollama or vLLM or cloud LLM providers.

19Updated 3 days ago

Docker · Web#Browser automation#MCP#Multi-agent workflows

A local voice AI agent runs on Raspberry Pi with Ollama models, custom automation tools, and spoken confirmation for sensitive actions.

356Updated 3 months agoGPL-3.0

Linux · Web#Human approval#Ollama integration#Tool calling

A local AI agent app that saves memories only with your approval and works with Claude, ChatGPT or local models through OpenAI-compatible endpoints.

463Updated 1 week agoApache-2.0

macOS · Windows · Linux · Web#Agent Skills#Human approval#MCP

Favicon of OpenClaw

OpenClaw

72 videos
A self-hosted AI assistant that connects to messaging apps, supports local and hosted models, and keeps memory on your hardware.

394.4KUpdated 20 hours agoMIT

macOS · Windows · Linux · iOS · Android · Docker#Multi-user access#Persistent memory#Tool calling

Favicon of OpenFang

OpenFang

1 video
A self-hosted AI agent platform that runs scheduled tasks on macOS, Windows and Linux, with local models through Ollama, vLLM or LM Studio.

18.3KUpdated 6 months agoApache-2.0

macOS · Windows · Linux · Docker · Web#Guardrails#Human approval#Knowledge graphs

Favicon of Newelle

Newelle

1 video
A Linux AI assistant that runs models offline through Ollama or Llama.cpp, with document search, local voice tools and MCP support.

1.5KUpdated 1 week agoGPL-3.0

Linux#Agent Skills#Code execution#Hybrid search

Desktop AI agent for macOS and Linux with local memory, computer tools, Ollama models and cloud provider connections. Apache 2.0 licensed.

6.9KUpdated 1 month agoApache-2.0

macOS · Windows · Linux · Web#Agent Skills#Code execution#Multi-agent workflows

A self-hosted personal AI agent keeps memory on your machine, works between conversations, and supports Ollama, vLLM and cloud model providers.

2.5KUpdated 21 hours agoMIT

Windows · Linux · Docker · Web#Agent Skills#Code execution#Guardrails

A desktop AI client for macOS that combines offline Ollama chat with cloud models using your own API keys, plus coding and research tools.

0Updated 3 months agoMIT

macOS#Agent Skills#Browser automation#Code execution

Favicon of Odysseus

Odysseus

21 videos
A self-hosted AI workspace combines local or API model chat, autonomous agents, research and email, with Docker deployment and no telemetry.

95.6KUpdated 23 hours agoAGPL-3.0

Docker · Web#Agent Skills#Code execution#MCP

A local AI agent browses the web, writes and runs code, and plans tasks using Ollama, LM Studio or an OpenAI-compatible server.

27.7KUpdated 3 weeks agoGPL-3.0

macOS · Windows · Linux · Docker · Web#Browser automation#Code execution#llama.cpp backend

A local-first AI journal organizes text, photos, and voice on iOS and Android, with Ollama support for offline use and portable Markdown storage.

838Updated 1 day agoGPL-3.0

iOS · Android#Code execution#Multi-agent workflows#Multimodal input

A local AI agent runs tasks across files, code, and browsers, with persistent memory, approval controls, and support for Ollama or cloud models.

883Updated 2 months agoAGPL-3.0

macOS · Windows · Linux · Web#Agent Skills#Browser automation#Code execution

A self-hosted AI agent server with persistent memory, sandboxed tools and voice, supporting local models and cloud providers on macOS, Linux and Windows.

3KUpdated 3 weeks agoMIT

macOS · Windows · Linux · Docker · Web#Agent Skills#Code execution#GGUF

A self-hosted personal AI assistant that reads local Markdown notes, runs with Ollama, and pairs with a mobile browser app on your phone.

4Updated 4 months agoMIT

macOS · Windows · Linux · Docker · Web#Code execution#Human approval#Ollama integration

A self-hosted AI assistant for Nextcloud Hub handles documents, chat and calendar tasks with local models or cloud providers under AGPL-3.0.

95Updated 2 days agoAGPL-3.0

Web#Multi-user access#Multilingual#Multimodal input

A self-hosted AI assistant that searches and organizes your documents, notes, photos and tasks using local models, with optional cloud inference.

928Updated 6 months agoMIT

macOS · Windows · Linux · Docker · Web#llama.cpp backend#LM Studio integration#MLX

A self-hosted AI agent that triages incoming messages and organizes ongoing work in an Obsidian-compatible vault, using external model providers.

237Updated 2 months ago

macOS · Linux · Docker · Web#Context compression#Human approval#Knowledge graphs

Favicon of AnythingLLM

AnythingLLM

12 videos
A free local AI assistant for Windows, macOS, Linux and Android, with document chat, agents and a Docker option for self-hosted teams.

68.3KUpdated 23 hours agoMIT

macOS · Windows · Linux · Android · Docker · Web#LM Studio integration#MCP#Multimodal input

A desktop or self-hosted AI agent under MIT with local model setup, persistent memory and background tasks. Remote model requests go directly to providers.

1.9KUpdated 1 day agoMIT

macOS · Windows · Linux · Docker · Web#Agent Client Protocol#Agent Skills#Code execution

A local AI assistant for Linux and macOS uses Ollama to execute tasks with approval controls, persistent memory and optional Ollama Cloud models.

getpurple.netComputer and Browser Agents

macOS · Linux#Code execution#Guardrails#Human approval

Desktop AI agent client for macOS, Windows and Linux that combines Claude Code, Codex and local models through Ollama, with locally stored chat history.

6.5KUpdated 2 months ago

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

A local AI chat app and agent for Apple Silicon Macs, with MLX models, file and shell tools, image input and optional Jina AI web search.

1.8KUpdated 2 weeks ago

macOS#Code execution#Hugging Face integration#MLX

A self-hosted AI agent platform runs offline with persistent memory, multi-framework chat, and shared compute across your own devices.

607Updated 2 days agoAGPL-3.0

macOS · Windows · Linux · iOS · Android · Web#Agent Skills#Distributed execution#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
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