head to head · open source

LobeChat vs vellum-assistant

LobeChat has 83,716 GitHub stars, 16,033 forks, 922 open issues and last shipped yesterday. vellum-assistant has 1,470 stars, 229 forks, 179 open issues and last shipped yesterday. LobeChat leads on adoption by 5,595% (83,716 vs 1,470 stars). LobeChat is written in TypeScript under a custom or non-standard licence; vellum-assistant is written in TypeScript under MIT. LobeChat has attracted 19% as many forks as stars, vellum-assistant 16%. vellum-assistant was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 2 topic tags (agent, claude), 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.

LobeChat ★ 84K vellum-assistant ★ 1.5K category AI & Machine Learning

← all 20902 open source comparisons

Side by side

LobeChat vellum-assistant
GitHub stars ★ 84K ★ 1.5K
License Custom / other MIT
Written in TypeScript TypeScript
Last push 2026-11-02 2026-11-02
Forks ⑂ 16K ⑂ 229
Self-hosting Yes Yes
Data ownership Your server Your server

pick LobeChat if

  • You weight community size — 84K stars and counting
  • You want the Custom / other license terms
  • Your stack matches TypeScript
  • You value the larger contributor base for long-term maintenance

full LobeChat profile →

pick vellum-assistant if

  • You want the vellum-assistant feature set and don't need the biggest community
  • You prefer the MIT license terms
  • Your stack matches TypeScript
  • You evaluated both and vellum-assistant fits your workflow better

full vellum-assistant profile →

About LobeChat

[![][image banner]][vercel link] LobeHub LobeHub organizes your agents into 7×24 operation. It hires, schedules, reports on your entire AI team. You stay in charge — without staying online. English · 简体中文 · [Official Site][official site] · [Changelog][changelog] · [Documents][docs] · [Blog][blog] · [Feedback][github issues link] [![][github release shield]][github release link] [![][docker release shield]][docker release link] [![][vercel shield]][vercel link] [![][discord shield]][discord link] [![][codecov shield]][codecov link] [![][github action test shield]][github action test link] [![][github action…

read the full LobeChat overview →

About vellum-assistant

A personal AI assistant that evolves with you. 8 different types of memory (episodic, semantic, procedural, emotional, prospective, behavioral, narrative, shared) make it truly yours. It learns how you work, remembers what matters, and takes action across your apps. What It Does If you've set up a Personal AI on OpenClaw, Hermes Agent, or Claude Code, you know how long it takes, and how many times you have to hatch a new one to get it right. Vellum gets you the result you're looking for out of the box, one download away. Get Started 1. Sign up or download the app The desktop app is available for macOS and…

read the full vellum-assistant 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 LobeChat or vellum-assistant more popular?

LobeChat has 83,716 GitHub stars and vellum-assistant has 1,470. LobeChat has the larger community by that measure.

Are LobeChat and vellum-assistant free?

Both are open source. LobeChat has no licence declared in this registry, and vellum-assistant is licensed under MIT. Both are free to self-host.

What is the difference between LobeChat and vellum-assistant?

LobeChat is written in TypeScript and vellum-assistant 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, LobeChat or vellum-assistant?

Choose LobeChat if you want the larger community (83,716 stars) or its Custom / other licence terms. Choose vellum-assistant if its feature set, stack or MIT licence fits better. Both are self-hostable.