Local and Self-Hosted Personal AI Assistants

Find AI assistants you can run locally or self-host for recurring tasks, research and app automation. Compare integrations and what each app can actually do.

36 tools
Favicon of nanobot

nanobot

2 videos
A self-hosted personal AI agent combines file and shell tools, long-term memory, scheduled tasks and chat app connections under an MIT license.

50KUpdated 19 hours agoMIT

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

Favicon of Hermes Agent

Hermes Agent

96 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.

262.1KUpdated 21 hours agoMIT

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

An open-source AI agent framework builds agents and workflows from plain-language requests, with Docker-based execution and a choice of model APIs.

9.8KUpdated 1 year agoMIT

Docker#Multi-agent workflows#OpenAI-compatible API#RAG

Desktop AI assistant for macOS, Windows and Linux that connects to Ollama or cloud models and supports a local document knowledge base and MCP tools.

5.4KUpdated 5 days ago

macOS · Windows · Linux#MCP#Multilingual#Ollama integration

A self-hosted AI research agent develops ideas, runs experiments and drafts papers, with a browser interface and cloud model access through OpenRouter.

5.9KUpdated 1 year ago

Linux · Docker · Web#Code execution#Multi-agent workflows#Web search

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

880Updated 2 months agoAGPL-3.0

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

A native Mac AI assistant automates apps and searches documents, with fully offline models through Ollama, LM Studio or MLX and optional cloud AI.

enconvo.comAI Workflow Automation

macOS · iOS#LM Studio integration#MCP#MLX

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.

18.2KUpdated 6 months agoApache-2.0

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

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

Favicon of OpenWork

OpenWork

1 video
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 20 hours ago

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

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

1.3KUpdated 4 days agoApache-2.0

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

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

2Updated 2 months agoMIT

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

Favicon of PicoClaw

PicoClaw

2 videos
Self-hosted AI assistant for small Linux devices, desktops and Android. Connects to local models through Ollama or vLLM, plus hosted providers.

30.1KUpdated 3 months agoMIT

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

Favicon of OpenClaw

OpenClaw

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

394.3KUpdated 21 hours agoMIT

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

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

27.6KUpdated 3 weeks agoGPL-3.0

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

A local AI desktop workspace for documents, email and code, with GGUF and Apple Silicon MLX models and optional cloud providers.

46Updated 1 day agoAGPL-3.0

macOS · Windows · Linux · Browser Extension#Code execution#GGUF#llama.cpp backend

Favicon of OpenManus

OpenManus

2 videos
An open-source AI agent framework runs locally, connects to LLM APIs, and automates Chrome or Chromium through Browser Use.

58.9KUpdated 3 months agoMIT

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

A locally installed coding agent for macOS, Linux and Windows uses selected model providers, with sandboxed commands. Open source under Apache 2.0.

68.9KUpdated 2 days agoApache-2.0

macOS · Windows · Linux#Agent Client Protocol#Code execution#Human approval

An AI agent workspace offers Docker self-hosting and a hosted service, with parallel agent groups, scheduled tasks and editable memory.

84.6KUpdated 19 hours ago

Linux · Docker · Web#MCP#Multi-agent workflows#Multi-user access

A local voice assistant controls your Home Assistant smart home, with companion apps, dedicated hardware and optional cloud voice processing.

92.1KUpdated 23 hours agoApache-2.0

Linux · iOS · Android · Web#Home Assistant integration#Multilingual#Wake word detection

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 local LLM app runs compatible GGUF models offline on Android without an account, keeping local-model chats and approved Memory on your phone.

redpluglab.github.ioMobile Chat Apps

Android#GGUF#OpenAI-compatible API#Persistent memory

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.

33.3KUpdated 24 hours agoApache-2.0

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

A self-hosted AI companion app lets you customize characters and talk by voice or text, with local speech recognition and cloud language models.

6.2KUpdated 3 years agoMIT

macOS · Linux · iOS · Docker · Web#Voice cloning

Favicon of PraisonAI

PraisonAI

1 video
An AI agent framework builds multi-agent workflows with memory and tool access, using Ollama or cloud models and optional self-hosted Docker execution.

9.3KUpdated 5 days agoMIT

Docker#Code execution#Context compression#Guardrails

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

An AI agent framework runs locally with Ollama or cloud models to automate browser tasks, analyze documents, and execute Python.

20.2KUpdated 1 day ago

macOS · Windows · Linux · Docker · Web#Browser automation#Code execution#MCP

A local AI assistant for iPhone, iPad and Mac that supports offline voice chat and document questions, with optional cloud models through OpenRouter.

enclaveai.appChat With Your Documents

macOS · iOS#Works offline

Favicon of AnythingLLM

AnythingLLM

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

68.1KUpdated 23 hours agoMIT

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

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

93Updated 1 day agoAGPL-3.0

Web#Multi-user access#Multilingual#Multimodal input

Favicon of Leon

Leon

1 video
A self-hosted AI assistant for Linux, macOS and Windows that automates tasks through skills and supports local models and offline voice tools.

17.7KUpdated 3 days agoMIT

macOS · Windows · Linux · Web#Persistent memory#Tool calling

A self-hosted AI agent that runs on macOS, Windows and Linux, with offline Ollama models, cloud provider support and shared chat across messaging apps.

918Updated 2 weeks agoMIT

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

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

325Updated 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
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

Choose an assistant by the tasks it can perform

A useful personal assistant needs the right connection to your work: documents, desktop apps, messaging or home devices. Some support scheduled research and updates, while others act when you ask them. A chat interface on its own does not establish access to your calendar, notifications or other apps.

Start with one supported workflow and check which integrations it needs. Self-hosting gives you control of the assistant's service, but connected email, search and cloud models may still use external systems. Review what an assistant can read or change before giving it access, and check that its chosen model supports the tools required for that workflow.