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.

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

50.4KUpdated 16 hours agoMIT

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

Favicon of Hermes Agent

Hermes Agent

29 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.

254.7KUpdated 10 hours agoMIT

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

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 2 weeks ago

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

Favicon of Goose

Goose

3 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.

55.4KUpdated 1 day agoApache-2.0

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

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.

52.7KUpdated 15 hours agoAGPL-3.0

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

A self-hosted AI email assistant that sorts IMAP mail and drafts replies for review, with MIT licensing and support for Claude Code, Codex, Gemini and llm.

0Updated 3 weeks agoMIT

macOS · Windows · Linux#Human approval#Multilingual#Persistent memory

A local AI agent for browser and desktop automation on Windows, macOS and Linux, using Claude, Gemini, Kimi or MiniMax APIs. MIT licensed.

14.3KUpdated 2 days agoMIT

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

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

16KUpdated 4 months agoMIT

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

A desktop AI agent connects Ollama or cloud models to local tools and MCP servers on Windows, macOS and Linux, with an MIT license.

1.8KUpdated 3 months agoMIT

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

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.

17.6KUpdated 6 days agoMIT

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

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 Octop

Octop

2 videos
A self-hosted AI assistant for households and small teams, with personal agents, document search, and support for Ollama and OpenAI-compatible APIs.

9.8KUpdated 1 day agoMIT

macOS · Windows · Linux · Docker · Web#Agent Client Protocol#Browser automation#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.

106Updated 2 weeks agoAGPL-3.0

Android#Agent Skills#Code execution#Knowledge graphs

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

926Updated 5 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.

234Updated 1 month ago

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

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

151Updated 1 week agoMIT

Windows#Agent Skills#Code execution#MCP

Favicon of OpenHuman

OpenHuman

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

42.1KUpdated 1 day agoGPL-3.0

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

Favicon of Odysseus

Odysseus

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

93.8KUpdated 2 days agoAGPL-3.0

Docker · Web#Agent Skills#Code execution#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

A self-hosted AI agent runtime connects to Ollama or hosted models, with desktop and browser chat, messaging channels and .NET extensions.

525Updated 4 days agoMIT

macOS · Windows · Linux · Docker · Web#Agent Skills#Human approval#LLM tracing

A desktop AI agent workspace executes file and shell tasks locally or over SSH on Windows, macOS and Linux, using configured model providers.

2.8KUpdated 8 hours agoMIT

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

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 5 months agoApache-2.0

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

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

9Updated 2 days agoMIT

macOS#Guardrails#Human approval#MCP

Favicon of AnythingLLM

AnythingLLM

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

67.3KUpdated 3 days agoMIT

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

Favicon of nanobot

nanobot

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

49.1KUpdated 15 hours agoMIT

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

A self-hosted AI personal assistant that handles tasks by email or browser. Runs in Docker, uses OpenRouter, and is open source under Apache 2.0.

2Updated 6 days agoApache-2.0

Docker · Web#Code execution#Human approval#Persistent memory

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 8 months ago

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

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

5.7KUpdated 1 week agoMIT

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

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

325Updated 7 months agoMIT

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

Favicon of LM Studio

LM Studio

53 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

A local AI assistant for Apple Silicon Macs that turns email into tasks, organizes files and transcribes meetings using built-in models or Ollama.

1Updated 5 months ago

macOS#Multimodal input#Ollama integration#Persistent memory

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

201Updated 2 weeks ago

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

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.

11Updated 3 days agoAGPL-3.0

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

Favicon of QM

QM

1 video
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.

15.4KUpdated 16 hours agoMIT

Web#Agent Skills#Code execution#Git integration

An MIT-licensed desktop AI agent for macOS and Windows that operates on local files and projects, saves sessions locally, and accepts requests from chat apps.

6.1KUpdated 2 days agoMIT

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

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

581Updated 5 days agoAGPL-3.0

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

More in Chat and Assistants