head to head · open source
AnythingLLM vs koishi
AnythingLLM has 66,155 GitHub stars, 7,348 forks, 311 open issues and last shipped yesterday. koishi has 6,208 stars, 348 forks, 107 open issues and last shipped 21 days ago. AnythingLLM leads on adoption by 966% (66,155 vs 6,208 stars). AnythingLLM is written in JavaScript under MIT; koishi is written in TypeScript under MIT. AnythingLLM has attracted 11% as many forks as stars, koishi 6%. AnythingLLM was the more recently maintained of the two, and both are self-hostable with no licence fee.
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 8884 open source comparisons
Side by side
| AnythingLLM | koishi | |
|---|---|---|
| GitHub stars | ★ 66K | ★ 6.2K |
| License | MIT | MIT |
| Written in | JavaScript | TypeScript |
| Last push | 2026-09-17 | 2026-08-28 |
| Forks | ⑂ 7.3K | ⑂ 348 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick AnythingLLM if
- You weight community size — 66K stars and counting
- You want the MIT license terms
- Your stack matches JavaScript
- You value the larger contributor base for long-term maintenance
pick koishi if
- You want the koishi feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches TypeScript
- You evaluated both and koishi fits your workflow better
About AnythingLLM
AnythingLLM is a local first AI application that enables users to chat with their documents using any large language model (LLM), local or cloud hosted. It runs as a self hosted service—by default in Docker—and provides a complete interface for document ingestion, agent orchestration, multi user access, and workflow automation without requiring external cloud dependencies. The project lives in the local AI and AI interaction ecosystem, targeting users who want full control over their data and model selection.
read the full AnythingLLM overview →
About koishi
Koishi is a cross platform, extensible, high performance chatbot framework written in TypeScript, aimed at anyone who wants to build and run bots across QQ, Telegram, Discord, Feishu, Matrix, LINE, mail and OneBot from one codebase.
read the full koishi 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 koishi more popular?
AnythingLLM has 66,155 GitHub stars and koishi has 6,208. AnythingLLM has the larger community by that measure.
Are AnythingLLM and koishi free?
Both are open source. AnythingLLM is licensed under MIT and koishi under MIT. Neither carries a licence fee.
What is the difference between AnythingLLM and koishi?
AnythingLLM is written in JavaScript and koishi 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 koishi?
Choose AnythingLLM if you want the larger community (66,155 stars) or its MIT licence terms. Choose koishi if its feature set, stack or MIT licence fits better. Both are self-hostable.