head to head · open source
QwenPaw vs koishi
QwenPaw has 35,130 GitHub stars, 3,119 forks, 990 open issues and last shipped today. koishi has 6,213 stars, 350 forks, 107 open issues and last shipped 23 days ago. QwenPaw leads on adoption by 465% (35,130 vs 6,213 stars). QwenPaw is written in TypeScript under Apache-2.0; koishi is written in TypeScript under MIT. QwenPaw has attracted 9% as many forks as stars, koishi 6%. QwenPaw was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 1 topic tag (chatbot), 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
| QwenPaw | koishi | |
|---|---|---|
| GitHub stars | ★ 35K | ★ 6.2K |
| License | Apache-2.0 | MIT |
| Written in | TypeScript | TypeScript |
| Last push | 2026-09-20 | 2026-08-28 |
| Forks | ⑂ 3.1K | ⑂ 350 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick QwenPaw if
- You weight community size — 35K stars and counting
- You want the Apache-2.0 license terms
- Your stack matches TypeScript
- 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 QwenPaw
QwenPaw is a personal AI assistant harness under the Apache 2.0 licence, aimed at people who want an LLM agent running on their own machine or in their own cloud account and reachable from the chat apps they already use.
read the full QwenPaw 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 QwenPaw or koishi more popular?
QwenPaw has 35,130 GitHub stars and koishi has 6,213. QwenPaw has the larger community by that measure.
Are QwenPaw and koishi free?
Both are open source. QwenPaw is licensed under Apache-2.0 and koishi under MIT. Neither carries a licence fee.
What is the difference between QwenPaw and koishi?
QwenPaw is written in TypeScript 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, QwenPaw or koishi?
Choose QwenPaw if you want the larger community (35,130 stars) or its Apache-2.0 licence terms. Choose koishi if its feature set, stack or MIT licence fits better. Both are self-hostable.