AnythingLLM vs LobeHub (formerly LobeChat) vs Jan

Side by side, as alternatives to ChatGPT Plus. Rows that differ are highlighted; the strongest value in a row is marked. Unknown means no source yet.

AnythingLLMMintplex-Labs/anything-llm

LobeHub (formerly LobeChat)lobehub/lobehub

Janjanhq/jan

ChatGPT Pluspaid product

Cost and coverage

Price

$0 software; you run it

Plus $20/month; Pro from $100/month source ↗

Chat assistant

Partly

Yes

Chat with your documents

Partly

Yes

Web search answers

Yes

Jobs covered

2 of 3 jobs

1 of 3 jobs

All 3

Popularity and activity (from GitHub)

Stars

67,366

83,366Top

45,023

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

123

1,103Top

195

—

Latest release

v1.18.0 · 2026-10-13

v2.2.20 · 2026-10-18

v0.8.7 · 2026-10-20Top

—

Commits / 12 wk

299

3,046

748

—

People committing / 12 mo

55+

129+

46+

—

Issues opened / closed, 30 days

174 / 155

103 / 52

119 / 137

—

Facts, with sources on each project page

Runs on my machine?Differs

Yes, desktop app or Docker; local by default

Yes, self-hosted via Docker; desktop app also available

Yes, desktop app running models offline

Hosted by the vendor

Code licenceDiffers

MIT

LobeHub Community License (Apache-2.0 + conditions); not OSI-approved

Apache-2.0 (attribution requested)

—

Model weights licenceDiffers

No bundled chat weights; licence depends on the model you pick

No bundled weights; licence depends on the model or API you connect

No bundled weights; licence depends on the model you download

—

Commercial useDiffers

Yes, MIT code; check the licence or terms of the model you use

Unmodified commercial use OK; distributing derivatives needs a paid licence

Yes, Apache-2.0 app; check the licence of the model you use

—

Paid services needed?Differs

None required; local LLM, embedder and vector DB by default; cloud optional

Self-host guide requires an OpenAI key; local Ollama documented as alternative

None required; cloud model providers optional

Subscription

HardwareDiffers

Recommended 16GB RAM, 8-core CPU; GPU recommended on Windows; storage varies by model

Docker Compose self-hosting: minimum 2 CPU cores, 4 GB RAM, 20 GB storage; production 4+ cores, 8+ GB RAM, 50+ GB storage

macOS 8GB RAM for 3B, 16GB for 7B, 32GB for 13B models; GPU optional

—

Operating systemsDiffers

Desktop for Mac, Windows and Linux; Docker for servers

Docker self-host; desktop app on Windows, macOS, some Linux distributions

Windows 10+, macOS 13.6+, Linux (deb, AppImage, Flathub)

—

Setup effortDiffers

Easy; desktop installer, or Docker for multi-user

Medium; setup script + docker compose, or one-click cloud deploy

Easy; download installer (exe, dmg, deb, AppImage) or app stores

—

Stars over time

Switch to Growth % to compare projects of different sizes fairly.

AnythingLLM
LobeHub (formerly LobeChat)
Jan

Focus a point, use arrow keys, or tap for its value.

Tracked daily since 15 Oct 2026. Dashed history: estimated from public records of when people starred the repo. Lines connect observations only; gaps contain no measured points.

Growth % starts at each project's first observed point in the shown range. Zero-star starts are unavailable.

Notes for a video or post

A plain summary with today's date and a link to the sources. Check each project page before you publish.

AnythingLLM vs LobeHub (formerly LobeChat) vs Jan (as alternatives to ChatGPT Plus)
Figures from RepoQuarry, 21 Oct 2026. Sources: https://repoquarry.dev/compare?ids=anything-llm,lobehub,jan&product=chatgpt-plus

ChatGPT Plus: Plus $20/month; Pro from $100/month
AnythingLLM: free software; does 2 of 3 ChatGPT Plus jobs
LobeHub (formerly LobeChat): free software; does 1 of 3 ChatGPT Plus jobs
Jan: free software; does 1 of 3 ChatGPT Plus jobs

- AnythingLLM: 67,366 GitHub stars, 299 commits in 12 weeks, licence MIT
- LobeHub (formerly LobeChat): 83,366 GitHub stars, 3,046 commits in 12 weeks, licence LobeHub Community License (Apache-2.0 + conditions); not OSI-approved
- Jan: 45,023 GitHub stars, 748 commits in 12 weeks, licence Apache-2.0 (attribution requested)

Where they differ:
- Runs on my machine?: AnythingLLM Yes, desktop app or Docker; local by default; LobeHub (formerly LobeChat) Yes, self-hosted via Docker; desktop app also available; Jan Yes, desktop app running models offline
- Code licence: AnythingLLM MIT; LobeHub (formerly LobeChat) LobeHub Community License (Apache-2.0 + conditions); not OSI-approved; Jan Apache-2.0 (attribution requested)
- Model weights licence: AnythingLLM No bundled chat weights; licence depends on the model you pick; LobeHub (formerly LobeChat) No bundled weights; licence depends on the model or API you connect; Jan No bundled weights; licence depends on the model you download
- Commercial use: AnythingLLM Yes, MIT code; check the licence or terms of the model you use; LobeHub (formerly LobeChat) Unmodified commercial use OK; distributing derivatives needs a paid licence; Jan Yes, Apache-2.0 app; check the licence of the model you use
- Paid services needed?: AnythingLLM None required; local LLM, embedder and vector DB by default; cloud optional; LobeHub (formerly LobeChat) Self-host guide requires an OpenAI key; local Ollama documented as alternative; Jan None required; cloud model providers optional
- Hardware: AnythingLLM Recommended 16GB RAM, 8-core CPU; GPU recommended on Windows; storage varies by model; LobeHub (formerly LobeChat) Docker Compose self-hosting: minimum 2 CPU cores, 4 GB RAM, 20 GB storage; production 4+ cores, 8+ GB RAM, 50+ GB storage; Jan macOS 8GB RAM for 3B, 16GB for 7B, 32GB for 13B models; GPU optional
- Operating systems: AnythingLLM Desktop for Mac, Windows and Linux; Docker for servers; LobeHub (formerly LobeChat) Docker self-host; desktop app on Windows, macOS, some Linux distributions; Jan Windows 10+, macOS 13.6+, Linux (deb, AppImage, Flathub)
- Setup effort: AnythingLLM Easy; desktop installer, or Docker for multi-user; LobeHub (formerly LobeChat) Medium; setup script + docker compose, or one-click cloud deploy; Jan Easy; download installer (exe, dmg, deb, AppImage) or app stores

Stars show popularity, not quality. Check each project page before publishing.

Want share images and a ready video description? Open a project's creator kit.

Numbers: GitHub, fetched nightly. Facts: read from each project's own documentation, with the source on its page. How we check. Mintplex-Labs/anything-llm ↗lobehub/lobehub ↗janhq/jan ↗

AnythingLLM vs LobeHub (formerly LobeChat) vs Jan

Stars over time

Notes for a video or post

Cookie preferences

Report a problem