# Bonsai-demo | PrismML-Eng | Knowledge Base | Instagit

Bonsai Demo

GitHub Stars: 1.7k

Repository: https://github.com/PrismML-Eng/Bonsai-demo

---

## Articles

### [Setting Up Hugging Face and DeepWiki MCP Servers with Per-Chat Opt-In in Bonsai](/PrismML-Eng/Bonsai-demo/setting-up-hugging-face-and-deepwiki-mcp-servers-with-per-chat-opt-in)

Easily set up Hugging Face and DeepWiki MCP servers with per-chat opt-in in Bonsai. Control token costs by enabling these AI tools only when needed for specific conversations via Open WebUI.

- Tags: how-to-guide
- Published: 2026-07-17

### [How Prompt Cache Reuse Works in Bonsai-Demo and When It’s Disabled in Speculative Mode](/PrismML-Eng/Bonsai-demo/how-does-prompt-cache-reuse-work-and-when-is-it-disabled-in-speculative-mode)

Discover how prompt cache reuse speeds up API calls by caching tokenized prompts in Bonsai-demo. Learn when speculative mode disables this optimization for crucial reprocessing.

- Tags: internals
- Published: 2026-07-17