head to head · open source
AnythingLLM vs locally-uncensored
AnythingLLM has 67,862 GitHub stars, 7,658 forks, 311 open issues and last shipped 4 days ago. locally-uncensored has 3,183 stars, 511 forks, 7 open issues and last shipped yesterday. AnythingLLM leads on adoption by 2,032% (67,862 vs 3,183 stars). AnythingLLM is written in JavaScript under MIT; locally-uncensored is written in TypeScript under AGPL-3.0. AnythingLLM has attracted 11% as many forks as stars, locally-uncensored 16%. locally-uncensored was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 2 topic tags (llm, local-ai), so they are genuine substitutes rather than adjacent tools.
Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.
← all 20902 open source comparisons
Side by side
| AnythingLLM | locally-uncensored | |
|---|---|---|
| GitHub stars | ★ 68K | ★ 3.2K |
| License | MIT | AGPL-3.0 |
| Written in | JavaScript | TypeScript |
| Last push | 2026-10-30 | 2026-11-02 |
| Forks | ⑂ 7.7K | ⑂ 511 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick AnythingLLM if
- You weight community size — 68K stars and counting
- You want the MIT license terms
- Your stack matches JavaScript
- You value the larger contributor base for long-term maintenance
pick locally-uncensored if
- You want the locally-uncensored feature set and don't need the biggest community
- You prefer the AGPL-3.0 license terms
- Your stack matches TypeScript
- You evaluated both and locally-uncensored fits your workflow better
About AnythingLLM
[!NOTE] We are also working on Open Computer which gives an entire computer environment for AI Agents to use. This will bring AnythingLLM's agent capabilities to a new level and a novel UX paradigm for AI Agent use. ⭐ Star the repo to stay updated! AnythingLLM: The all in one AI app you were looking for. Chat with your docs, use AI Agents, hyper configurable, multi user, & no frustrating setup required. Docs Hosted Instance English · 简体中文 · 日本語 👉 AnythingLLM for desktop (Mac, Windows, & Linux)! Download Now Chat with your docs. Automate complex workflows with AI Agents. Hyper configurable, multi user ready…
read the full AnythingLLM overview →
About locally-uncensored
Locally Uncensored The all in one local AI studio for your desktop. Chat, images, video and a coding agent in one app. Install it, pick a model, go. Free, open source, Windows and Linux. Everything runs on your own machine. No Docker, no terminal, no config files. Download · Three steps · What is in the box · How it compares · Models · FAQ Download Take the latest build from Releases. Some antivirus engines flag unsigned NSIS installers that download other binaries, which is a false positive. The installer is built by GitHub Actions from the public source on master , and the update channel is signed against a…
read the full locally-uncensored overview →
More in AI & Machine Learning
Related comparisons
More AI Interaction & Interfaces projects
Compare either of these against the rest of the AI Interaction & Interfaces field.
Frequently asked questions
Is AnythingLLM or locally-uncensored more popular?
AnythingLLM has 67,862 GitHub stars and locally-uncensored has 3,183. AnythingLLM has the larger community by that measure.
Are AnythingLLM and locally-uncensored free?
Both are open source. AnythingLLM is licensed under MIT and locally-uncensored under AGPL-3.0. Neither carries a licence fee.
What is the difference between AnythingLLM and locally-uncensored?
AnythingLLM is written in JavaScript and locally-uncensored in TypeScript. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, AnythingLLM or locally-uncensored?
Choose AnythingLLM if you want the larger community (67,862 stars) or its MIT licence terms. Choose locally-uncensored if its feature set, stack or AGPL-3.0 licence fits better. Both are self-hostable.