Self-hosted alternatives to ChatGPT

Every prompt is a data point on someone else's balance sheet, and the model changes under you without notice.

Below are 10 open-source projects that cover the same ground, each scored 0–100 on how actively it is actually maintained — commit volume, release cadence and recent trend. 10 of the 10 are currently rated healthy or better. Ordering reflects that score, not sponsorship.

Shortest path: Open-WebUI is the best-maintained option here (health 99/100). User-friendly AI Interface, supports Ollama, OpenAI API.
Project Health Activity (11 mo) Stars Licence Last release
Open-WebUI
User-friendly AI Interface, supports Ollama, OpenAI API.
Thriving · 99 2025-12: 322 commits 2026-01: 280 commits 2026-02: 505 commits 2026-03: 503 commits 2026-04: 387 commits 2026-05: 309 commits 2026-06: 439 commits 2026-07: 675 commits 2026-08: 552 commits 2026-09: 508 commits 2026-10: 1252 commits 159k BSD-3-Clause 17 Nov 2026
LobeHub
Modern design AI chat framework supporting multiple AI providers, one click install MCP Marketplace and Artifa
Thriving · 99 2025-12: 546 commits 2026-01: 940 commits 2026-02: 378 commits 2026-03: 438 commits 2026-04: 583 commits 2026-05: 733 commits 2026-06: 741 commits 2026-07: 889 commits 2026-08: 731 commits 2026-09: 928 commits 2026-10: 1320 commits 86k ⊘ Proprietary 18 Nov 2026
LocalAI
Run your AI models locally and generate images and audio (alternative to OpenAI and Claude).
Thriving · 97 2025-12: 195 commits 2026-01: 182 commits 2026-02: 179 commits 2026-03: 272 commits 2026-04: 288 commits 2026-05: 337 commits 2026-06: 365 commits 2026-07: 461 commits 2026-08: 379 commits 2026-09: 586 commits 2026-10: 503 commits 50k MIT 18 Nov 2026
LibreChat
Enhanced ChatGPT-compatible AI chat interface supporting multiple AI providers, with multi-user auth, message
Thriving · 96 2025-12: 0 commits 2026-01: 0 commits 2026-02: 0 commits 2026-03: 192 commits 2026-04: 137 commits 2026-05: 243 commits 2026-06: 279 commits 2026-07: 194 commits 2026-08: 472 commits 2026-09: 553 commits 2026-10: 727 commits 47k MIT 26 Oct 2026
Onyx Community Edition
Chat UI that works with any LLM. It comes loaded with advanced features like agents, web search, RAG, MCP, dee
Thriving · 94 2025-12: 478 commits 2026-01: 546 commits 2026-02: 567 commits 2026-03: 559 commits 2026-04: 556 commits 2026-05: 514 commits 2026-06: 612 commits 2026-07: 640 commits 2026-08: 442 commits 2026-09: 481 commits 2026-10: 949 commits 33k MIT 16 Nov 2026
Agenta
LLMOps platform for prompt management, LLM evaluation, and observability. Build, evaluate, and monitor product
Thriving · 93 2025-12: 1308 commits 2026-01: 1313 commits 2026-02: 1527 commits 2026-03: 1427 commits 2026-04: 735 commits 2026-05: 1385 commits 2026-06: 1533 commits 2026-07: 1927 commits 2026-08: 3209 commits 2026-09: 4093 commits 2026-10: 2663 commits 4.9k MIT 18 Nov 2026
Ollama
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.
Thriving · 91 2025-12: 78 commits 2026-01: 105 commits 2026-02: 110 commits 2026-03: 123 commits 2026-04: 112 commits 2026-05: 43 commits 2026-06: 98 commits 2026-07: 94 commits 2026-08: 104 commits 2026-09: 110 commits 2026-10: 155 commits 188k MIT 9 Nov 2026
Local Deep Research
AI-powered deep research tool with multi-source search (arXiv, PubMed, web), PDF text extraction, and encrypte
Thriving · 91 2025-12: 783 commits 2026-01: 864 commits 2026-02: 497 commits 2026-03: 630 commits 2026-04: 342 commits 2026-05: 433 commits 2026-06: 437 commits 2026-07: 268 commits 2026-08: 246 commits 2026-09: 355 commits 2026-10: 596 commits 9.6k MIT 15 Nov 2026
AnythingLLM
All-in-one desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibil
Thriving · 87 2025-12: 46 commits 2026-01: 57 commits 2026-02: 51 commits 2026-03: 92 commits 2026-04: 72 commits 2026-05: 42 commits 2026-06: 114 commits 2026-07: 147 commits 2026-08: 82 commits 2026-09: 126 commits 2026-10: 148 commits 68k MIT 17 Nov 2026
GoModel
AI gateway written in Go with a unified OpenAI-compatible API for multiple LLM providers, USD cost tracking, b
Healthy · 77 2025-12: 0 commits 2026-01: 0 commits 2026-02: 0 commits 2026-03: 0 commits 2026-04: 0 commits 2026-05: 53 commits 2026-06: 77 commits 2026-07: 152 commits 2026-08: 149 commits 2026-09: 221 commits 2026-10: 171 commits 1.3k MIT 18 Nov 2026

How these were picked

Every project listed here is open source and can run entirely on hardware you control. We start from the categories that match ChatGPT's job — Generative Artificial Intelligence (GenAI) — then rank by health score so that a popular-but-abandoned project never appears above a smaller one that is actively shipping. The scoring method is documented in full.

The scores are recomputed from repository data on every rebuild, so this page reflects the state of these projects as of 20 Nov 2026 — not the day it was written.

Open-WebUI

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

Best fit: It suits administrators who want a self-hosted graphical interface for local AI models without relying on third-party web services.

Worth knowing: Running local models requires significant hardware resources, and managing multiple backend integrations can introduce unexpected configuration overhead.

Full health breakdown for Open-WebUI →

LobeHub

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

Best fit: Teams or individuals looking for a customisable, self-hosted web interface to interact with various generative AI APIs in one place.

Worth knowing: The software uses a proprietary licence, which may restrict how you can modify or redistribute the source code compared to standard open-source alternatives.

Full health breakdown for LobeHub →

LocalAI

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

Best fit: It suits developers and organisations who want to run generative AI workloads locally to maintain data privacy or bypass external service costs.

Worth knowing: You will need to provide your own compatible hardware, such as GPUs, to achieve acceptable inference speeds. Running complex models locally can also introduce significant resource management overhead.

Full health breakdown for LocalAI →

LibreChat

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

Best fit: It suits administrators who want to host a centralised, multi-user AI chat interface with support for multiple upstream model providers.

Worth knowing: Managing API keys, user permissions, and upstream rate limits across multiple providers introduces ongoing operational overhead. It also duplicates the functionality of various native vendor applications.

Full health breakdown for LibreChat →

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.

Best fit: Self-hosters who want a feature-rich, unified chat front-end to interface with multiple external or local language models under an MIT licence.

Worth knowing: Integrating numerous knowledge connectors and running advanced agentic workflows can introduce significant configuration overhead and high resource consumption.

Full health breakdown for Onyx Community Edition →