Best self-hosted Generative Artificial Intelligence (GenAI) software in 2026

Generative Artificial Intelligence (GenAI) is a subset of artificial intelligence that uses generative models to produce text, images, videos, or other forms of data.

We track 14 open-source, self-hosted Generative Artificial Intelligence (GenAI) apps. 13 of them had commits in the last 90 days, 14 can run with Docker, and the most common licenses are MIT (9), Apache-2.0 (2), BSD-3-Clause (1). The most-used languages are Python, Nodejs, Go. Below are the top picks by GitHub stars, followed by every app ranked by stars weighted by maintenance health.

Alternatives to ChatGPTAlternatives to ClaudeAlternatives to GeminiAlternatives to Microsoft CopilotAlternatives to PerplexityAlternatives to NotebookLMAlternatives to LM Studio

Top 5 by GitHub stars

#AppStarsHealthLast activityLicenseLanguageDocker
1Ollama186.9kActive2026-11-09MITDocker, Python✓
2Open-WebUI158.6kActive2026-11-08BSD-3-ClauseDocker, Python✓
3LobeHub85.5kActive2026-11-10⊘ ProprietaryNodejs, Docker✓
4AnythingLLM68.3kActive2026-11-09MITNodejs, Docker✓
5LocalAI50.4kActive2026-11-10MITDocker, K8S✓
  1. Ollama — Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.
  2. Open-WebUI — User-friendly AI Interface, supports Ollama, OpenAI API.
  3. LobeHub — Modern design AI chat framework supporting multiple AI providers, one click install MCP Marketplace and Artifacts / Thinking.
  4. AnythingLLM — All-in-one desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
  5. LocalAI — Run your AI models locally and generate images and audio (alternative to OpenAI and Claude).

Head-to-head comparisons

Ollama vs Open-WebUILobeHub vs OllamaAnythingLLM vs OllamaLobeHub vs Open-WebUIAnythingLLM vs Open-WebUIAnythingLLM vs LobeHub

All 14 self-hosted Generative Artificial Intelligence (GenAI) apps

Ranked by GitHub stars weighted by maintenance health.

Ollama

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.

Active ★ 186.9k MIT 🐳 Docker~$40/mo

Open-WebUI

User-friendly AI Interface, supports Ollama, OpenAI API.

Active ★ 158.6k BSD-3-Clause 🐳 Docker~$40/mo

LobeHub

Modern design AI chat framework supporting multiple AI providers, one click install MCP Marketplace and Artifacts / Thinking.

Active ★ 85.5k ⊘ Proprietary 🐳 Docker~$40/mo

AnythingLLM

All-in-one desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

Active ★ 68.3k MIT 🐳 Docker~$40/mo

LocalAI

Run your AI models locally and generate images and audio (alternative to OpenAI and Claude).

Active ★ 50.4k MIT 🐳 Docker~$40/mo

LibreChat

Enhanced ChatGPT-compatible AI chat interface supporting multiple AI providers, with multi-user auth, message search, and plugin support.

Active ★ 47.1k MIT 🐳 Docker~$40/mo

Vane

AI-powered search engine (alternative to Perplexity AI).

Active ★ 38.2k MIT 🐳 Docker~$40/mo

Onyx Community Edition

Chat UI that works with any LLM. It comes loaded with advanced features like agents, web search, RAG, MCP, deep research, Connectors to 40+ knowledge sources, and more.

Active ★ 33.4k MIT 🐳 Docker~$40/mo

Local Deep Research

AI-powered deep research tool with multi-source search (arXiv, PubMed, web), PDF text extraction, and encrypted local storage.

Active ★ 9.6k MIT 🐳 Docker~$40/mo

Agenta

LLMOps platform for prompt management, LLM evaluation, and observability. Build, evaluate, and monitor production-grade LLM applications with collaborative prompt engineering.

Active ★ 4.9k MIT 🐳 Docker~$40/mo

Khoj

Your AI second brain. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI.

Maintained ★ 38.1k AGPL-3.0 🐳 Docker~$40/mo

LLM Harbor

Containerized LLM toolkit. Run LLM backends, APIs, frontends, and additional services via a concise CLI.

Active ★ 3.3k Apache-2.0 🐳 Docker~$40/mo

GoModel

AI gateway written in Go with a unified OpenAI-compatible API for multiple LLM providers, USD cost tracking, budgets, usage analytics, guardrails, caching, and an admin dashboard.

Active ★ 1.3k MIT 🐳 Docker~$40/mo

LLMKube

Kubernetes operator for LLM inference with pluggable runtimes (llama.cpp, vLLM, TGI, Ollama, vllm-swift), multi-GPU sharding, NVIDIA CUDA + Apple Silicon Metal support, and OpenAI-compatible API.

Active ★ 255 Apache-2.0 🐳 Docker~$40/mo

Frequently asked questions

What is the best self-hosted Generative Artificial Intelligence (GenAI) software in 2026?

By GitHub stars, the most popular self-hosted Generative Artificial Intelligence (GenAI) apps are Ollama (186,923 stars), Open-WebUI (158,608 stars), LobeHub (85,478 stars). Popularity is only one signal: also check maintenance health, license and whether it fits your setup.

How many self-hosted Generative Artificial Intelligence (GenAI) apps are actively maintained?

13 of the 14 apps listed had commits in the last 90 days and 1 more in the last 12 months.

Which self-hosted Generative Artificial Intelligence (GenAI) apps can I run with Docker?

14 of the 14 apps can run with Docker; 1 publish an image on Docker Hub, including GoModel.

Which licenses do self-hosted Generative Artificial Intelligence (GenAI) apps use?

The most common licenses in this category are MIT (9 apps), Apache-2.0 (2 apps), BSD-3-Clause (1 apps).

How much does it cost to self-host Generative Artificial Intelligence (GenAI) software?

The software itself is free to download. Based on our rough hardware estimates, the cheapest suitable VPS plan starts at about $40/month (median $40/month across apps in this category). Several light apps can share one server.

Figures from GitHub and Docker Hub as of 2026-11-15; hosting costs are rough estimates.