PerryLink DSH Plugin Family

Local AI

Run local AI models inside DeepSeek Harness: Ollama/LM Studio/local endpoints as drop-in model routes.

npm package
dsh-local-ai
Category
Models & routing
Version
0.2.18 from package.json
Licence
Apache-2.0 from package.json
Runtime
Node ^22.19.0 || >=24.0.0, DeepSeek Harness >=0.1.2-rc.1 <0.2.0 || >=0.1.5-alpha.1 <0.2.0 || >=0.1.6-0 <0.2.0 || >=0.1.7-0 <0.2.0 || >=0.2.0-rc.1 <0.3.0-0
Repository
PerryLink/dsh-local-ai

What it is

Local AI is a DeepSeek Harness plugin in the models & routing group, published to npm as `dsh-local-ai`. Run local AI models inside DeepSeek Harness: Ollama/LM Studio/local endpoints as drop-in model routes.

Version 0.2.18, licensed Apache-2.0, Node ^22.19.0 || >=24.0.0, DSH >=0.1.2-rc.1 <0.2.0 || >=0.1.5-alpha.1 <0.2.0 || >=0.1.6-0 <0.2.0 || >=0.1.7-0 <0.2.0 || >=0.2.0-rc.1 <0.3.0-0.

The repository is available as a local checkout, so the version and licence above are read from the package manifest that is actually published rather than from a registry copy.

Other plugins in the same group: Autotier, Laya.

Install

Install through the dsh plugin command; the two shells differ only in how the second line confirms the result.

bash / sh

dsh plugin --profile default add dsh-local-ai
dsh --profile default --dump-config | grep 'dsh-local-ai'

PowerShell

dsh plugin --profile default add dsh-local-ai
dsh --profile default --dump-config | Select-String 'dsh-local-ai'

Substitute your own profile name for default, then restart the session — installation alone does not hot-load the plugin.

Full documentation

This page covers what the plugin is, how to install it, and where it comes from. Configuration keys, tool schemas and the full manual live in the repository.

Full documentation → GitHub · 中文说明

More