300+ self-hosted AI apps, from local models to agents

Want to run AI models and agents on your own hardware instead of paying for a cloud service? This list has model runners such as Ollama, chat front ends such as Open WebUI, image tools such as ComfyUI, and agent and workflow builders such as Dify and Langflow. Each card shows the source model, pricing, estimated RAM and storage, and the last update. Use the filters to narrow the list.

showing 1–24 of 300 apps

appcategorysourcepricingest. ramest. storagelast update
Builds and runs AI agents as visual workflows triggered on demand, on schedules, or by external events. ai & ml +1source availablefree to self-host8 GB to 16 GB25 GB to 100 GBSep 24, 2026
staleWeb interface for generating and editing images with Stable Diffusion models. ai & ml +1open sourcefree to self-host8 GB to 16 GB20 GB to 200 GBFeb 9, 2025
Node-based interface for building and running local AI image, video, and audio workflows. ai & mlopen sourcefree to self-host8 GB to 32 GB20 GB to 100 GBSep 21, 2026
Plugin-based agent harness with a local web UI, CLI, SDK, and configurable model providers. ai & ml +1open sourcefree to self-host2 GB to 8 GB1 GB to 20 GBNov 13, 2026
Builds AI applications with visual workflows, retrieval pipelines, agents, model providers, tools, and published APIs. ai & ml +1source availablefreemium4 GB to 16 GB20 GB to 500 GBSep 10, 2026
Runs a personal AI agent from the terminal with tools, persistent memory, scheduled tasks, and messaging gateways. ai & ml +1open sourcefree to self-host1 GB to 4 GB2 GB to 20 GBSep 24, 2026
Visual builder for AI applications and agents with an API for running flows. ai & ml +1open sourcefree to self-host2 GB to 8 GB5 GB to 100 GBSep 22, 2026
Runs large language and vision-language models across a wide range of hardware. ai & mlopen sourcefree to self-host2 GB to 8 GB1 GB to 20 GBOct 28, 2026
Local model runtime with a CLI, HTTP API, and model library for running LLMs. ai & mlopen sourcefree to self-host4 GB to 16 GB10 GB to 100 GBJul 6, 2026
Web chat interface for using Ollama, OpenAI-compatible providers, tools, and knowledge files. ai & mlsource availablefreemium1 GB to 4 GB5 GB to 20 GBJul 1, 2026
Personal AI assistant that runs locally and responds through chat channels. ai & ml +1open sourcefree to self-host2 GB to 8 GB1 GB to 20 GBSep 23, 2026
Workspace for coordinating AI agents and their tasks. ai & ml +1open sourcefree to self-host2 GB to 8 GB1 GB to 20 GBNov 13, 2026
Provides a terminal coding agent and a TypeScript toolkit for building model-driven command-line agents. ai & ml +1open sourcefree to self-host512 MB to 4 GB1 GB to 20 GBSep 22, 2026
PostgreSQL extension for storing and searching vector embeddings. ai & ml +1open sourcefree to self-host2 GB to 4 GB10 GB to 30 GBNov 13, 2026
Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more. ai & mlopen sourcefree to self-host2 GB to 8 GB5 GB to 100 GBJun 25, 2026
Web crawler and scraper that turns websites into clean Markdown for LLMs, agents, and data pipelines. ai & ml +1open sourcepricing under review4 GB to 16 GB5 GB to 50 GBOct 14, 2026
archivedBuilds AI workflows and agents through a visual editor with model, tool, memory, retrieval, and API components. ai & ml +1open sourcefreemium2 GB to 8 GB1 GB to 50 GBJun 25, 2026
LiteLLM provides a proxy server to manage auth, loadbalancing, and spend tracking across 100+ LLMs, All in the OpenAI format. ai & ml +1open sourcefree to self-host8 GB to 32 GB20 GB to 100 GBOct 28, 2026
Toolkit for fine-tuning and serving large language and vision-language models with GPU acceleration. ai & ml +1open sourcefree to self-host8 GB to 32 GB20 GB to 100 GBMay 30, 2026
Schedules and monitors teams of AI agents that run recurring and on-demand work. ai & ml +1source availablefree to self-host4 GB to 16 GB20 GB to 200 GBNov 13, 2026
Local AI inference server with OpenAI-compatible APIs for text, image, and audio models. ai & ml +1open sourcefree to self-host3 GB to 6 GB3 GB to 10 GBJul 6, 2026
Adds persistent, searchable memory to AI agents and apps, so they remember user preferences and past interactions across sessions without pipeline changes. ai & mlopen sourcefree to self-host2 GB to 8 GB5 GB to 100 GBSep 25, 2026
Coordinates coding agents around shared tasks, repositories, branches, reviews, and human approvals. ai & ml +2source availablefree to self-host2 GB to 4 GB10 GB to 20 GBJul 17, 2026
Lightweight local AI agent runtime with WebUI, API, memory, tools, and chat integrations. ai & ml +1open sourcefree to self-host2 GB to 8 GB1 GB to 20 GBOct 28, 2026

How do you pick a self-hosted AI app?

Start with your hardware. Most model runners lean on a GPU, and a large model needs far more memory than the app itself. The RAM on each card is for the app, not the model you load, so check the model's size too.

  • Runner or front end. A chat front end needs a model runner or an API key behind it. Pick the runner first, then a front end that talks to it.
  • License. Some AI apps are source available or limit commercial use. Use the Source model filter, and check each model's license on its own, since whoever trained it sets that.
  • Health. AI projects move fast and stall fast. The Health filter shows which still get commits.
  • Docker. Using a GPU inside Docker takes extra setup, such as the NVIDIA Container Toolkit on Linux. Read the install docs before you choose Docker.

What should you plan for when you run one?

Models are big files, often several gigabytes each, so plan disk space for them. Before you open the app to the internet, check that it has its own login. If it doesn't, put one in front of it.