Give your cloud AI app an offline mode.
What it does
Adds a bundled local AI mode to an existing app by adapting its cloud API client to an embedded inference server.
When to use it
Use when an existing app calls a cloud AI service over HTTP and the user wants to bundle inference for the end user's PC, targeting Windows x64 or Linux x64.
How to use it
Give it an existing AI-enabled app; it adds a launcher, vendors the inference engine, and updates the existing client for local inference.
What you provide
- An existing project
Uses
Latest review
What you need · 1
Targets Windows x64 or Linux x64; macOS embeddable support is described as beta.
Access · 4
This skill
GitHub
Read
Downloads the latest Lemonade release
Embeddable Lemonade
Execute
Installs Embeddable Lemonade
llamacpp:vulkan
Execute
Installs the Vulkan inference backend