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 Goose

Goose

6 videos
An Apache 2.0 AI agent for macOS, Windows and Linux, with desktop and CLI interfaces and support for Ollama or cloud model providers.

56.6KUpdated 1 day agoApache-2.0

macOS · Windows · Linux#MCP#Multi-agent workflows#Ollama integration

An open-source AI assistant runs Gemma 4 offline on Android and desktop, with persistent memory, interactive screens and encrypted local chats.

1.4KUpdated 2 days agoApache-2.0

macOS · Windows · Linux · iOS · Android · Web#Code execution#LM Studio integration#MCP

Favicon of OpenWork

OpenWork

2 videos
A desktop AI agent app works on your files with cloud providers or local models through Ollama, and runs on macOS, Windows, and Linux.

24.5KUpdated 19 hours ago

macOS · Windows · Linux · Web#Agent Skills#Browser automation#MCP

An AI job application assistant evaluates postings, tailors CVs and prepares interviews through Claude Code, with local files and paid cloud AI access.

71.6KUpdated 2 days agoMIT

macOS · Windows · Linux#Agent Skills#Batch processing#Code execution

Favicon of Hermes Agent

Hermes Agent

105 videos
A self-hosted AI agent for macOS, Linux and Windows, with persistent memory, scheduled tasks and connections to hosted models or your own endpoint.

263.2KUpdated 19 hours agoMIT

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

A free MIT-licensed desktop AI agent for Windows and Apple Silicon macOS that uses cloud model APIs to work with files, documents and apps.

2.3KUpdated 4 weeks agoMIT

macOS · Windows · Linux#Agent Skills#Code execution#LLM tracing

Desktop AI agent that executes tasks on your machine and connects to Anthropic, OpenAI, OpenRouter or custom providers for model responses.

1.5KUpdated 4 months ago

#Agent Skills#Code execution#MCP

A self-hosted AI assistant with sandboxed agents, persistent memory and approval-based credential access that connects to your chosen LLM provider.

204Updated 2 days ago

Linux · Docker · Web#Code execution#Guardrails#Human approval

A desktop AI assistant for Windows, Linux and macOS that runs local Ollama models or uses cloud APIs, with agents, file search and code execution.

2KUpdated 1 month ago

macOS · Windows · Linux#Agent Skills#Code execution#MCP

Waku Agent

2 videos
A Python AI agent runs on your laptop with SQLite memory and editable MIT-licensed code. It uses remote model providers that require an API key.

2.2KUpdated 1 day agoMIT

Web#Agent Skills#LLM tracing#MCP

Favicon of Voxta

Voxta

1 video
An AI companion for voice chat, file tasks and interactive stories, with local or cloud processing on Windows and Linux.

voxta.aiAI Characters and Roleplay

Windows · Linux · Android · Web#Code execution#MCP#Multimodal input

An offline dictation app for Windows 10/11 that types into desktop apps and manages notes and reminders through a local AI assistant.

93Updated 3 weeks agoMIT

Windows#Hugging Face integration#llama.cpp backend#Multilingual

A local LLM chat app for Apple Silicon Macs that answers from your files, runs GGUF models offline, and supports optional remote model APIs.

3.3KUpdated 1 month agoMIT

macOS#GGUF#llama.cpp backend#OpenAI-compatible API

A self-hosted AI assistant that connects to Ollama and cloud models, manages personal records, and runs autonomous agents under the MIT license.

427Updated 2 months agoMIT

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

Favicon of QM

QM

3 videos
A self-hosted AI agent platform gives teams personal and shared workspaces in Slack and a web app, with MIT licensing and a choice of agent runtimes.

15.7KUpdated 20 hours agoMIT

Web#Agent Skills#Code execution#Git integration

Favicon of ZeroClaw

ZeroClaw

1 video
A self-hosted AI agent runs on Linux, macOS and Windows with local or cloud models, messaging integrations and approval controls for risky actions.

33.4KUpdated 1 day agoApache-2.0

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

Favicon of LM Studio

LM Studio

91 videos
A local LLM app runs downloaded models for chat and agent tasks, with MLX and llama.cpp support and voice transcription processed on your device.

lmstudio.aiComputer and Browser Agents

macOS · Windows · Linux#llama.cpp backend#MCP#MLX

Self-hosted AI agent runtime for Docker on macOS, Windows and Linux. Uses Ollama or cloud models, with local storage and reviewable actions.

93Updated 4 months agoApache-2.0

macOS · Windows · Linux · Docker · Web#Code execution#Context compression#Guardrails

A local AI assistant for iOS that chats offline with GGUF models, analyzes health data and statements, and connects to Ollama on a Mac.

33Updated 3 months agoApache-2.0

iOS#GGUF#Hugging Face integration#llama.cpp backend

An open-source local AI desktop runs GGUF models and agents on macOS and Windows, with offline file tools and optional cloud connections.

404Updated 4 weeks agoApache-2.0

macOS · Windows#Agent Skills#Code execution#GGUF

An open-source Python AI agent framework supports local models through Ollama, persistent memory, delegated agents and permission controls.

16.2KUpdated 5 months agoMIT

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

A local AI assistant that runs Ollama or hosted models, keeps records on your computer, and asks for approval before consequential actions.

1.7KUpdated 1 day agoApache-2.0

macOS · Windows · Linux · Web#Code execution#Human approval#Knowledge graphs

An iPhone control tool lets Codex on a Mac read screen text, manage the clipboard and control alarms through iMessage and Apple Shortcuts.

271Updated 3 months agoMIT

macOS · iOS#Agent Skills#Tool calling

An MIT-licensed assistant for Apple Silicon Macs with macOS 15+. Uses optional screen context, local memory and Ollama or GitHub Copilot inference.

10Updated 1 week agoMIT

macOS#Guardrails#Human approval#MCP

An Android AI agent with on-device memory and scheduled tasks that connects to cloud APIs or local models through Ollama and LM Studio.

126Updated 1 day agoAGPL-3.0

Android#Agent Skills#Code execution#Knowledge graphs

An open-source desktop AI chat app for Windows, macOS and Linux that connects to local models through Ollama or LM Studio and to cloud providers.

53.5KUpdated 24 hours agoAGPL-3.0

macOS · Windows · Linux#LM Studio integration#MCP#Multilingual

A local AI tool trains a personal model on your memories, with roleplay and permission-based connections to other AI identities and apps.

15.7KUpdated 1 year agoApache-2.0

macOS · Windows · Linux · Docker · Web#llama.cpp backend#MLX#Multi-agent workflows

A self-hosted AI learning agent with editable learner memory, a study wiki and scheduled review, supporting Ollama alongside cloud model providers.

1.5KUpdated 1 week agoMIT

macOS · Windows · Web#Agent Skills#Code execution#Hybrid search

A self-hosted AI agent for research, coding and data analysis, with Ollama or vLLM support, Docker code execution and an HTML editor.

1.6KUpdated 9 months ago

macOS · Windows · Linux · Docker#Code execution#Ollama integration#Persistent memory

A local AI work assistant framework extends coding agents with search across Slack, Jira and workplace documents using your existing accounts.

485Updated 4 months agoMIT

macOS#Agent Skills#Git integration#Human approval

A self-hosted AI agent with local memory, scheduled bots and coding tools that works with Ollama or cloud model providers.

3.9KUpdated 1 day agoMIT

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

A local AI memory app for Mac and Windows that searches screen history and meeting transcripts, with Ollama for offline AI and MCP access.

perfectmemory.aiAI Notes and Knowledge Bases

macOS · Windows#LM Studio integration#MCP#Ollama integration

Favicon of Khoj

Khoj

2 videos
A self-hostable AI assistant that searches documents and the web, supports local or online LLMs, and runs custom agents and scheduled automations.

38.1KUpdated 3 months agoAGPL-3.0

Web#RAG#Semantic search#Web search

A self-hosted AI mirror assistant with voice interaction and personal memory that can run locally with Ollama, VOICEVOX and local Whisper.

496Updated 10 months agoMIT

macOS · Docker · Web#Ollama integration#Persistent memory#RAG

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