mirror of https://github.com/openclaw/openclaw.git synced 2026-08-20 01:21:41 -06:00

Files

T

Dallin Romney dc911510ae chore(release): prepare 2026.6.33 npm rehearsal

Align the core package, plugin manifests, and npm shrinkwrap roots for the SHA-only extended-stable preflight. Native app versions remain on 2026.6.8 because no native release will be dispatched.

2026-07-09 19:23:21 -07:00

src

…

index.test.ts

…

index.ts

…

npm-shrinkwrap.json

chore(release): prepare 2026.6.33 npm rehearsal

2026-07-09 19:23:21 -07:00

openclaw.plugin.json

…

package.json

chore(release): prepare 2026.6.33 npm rehearsal

2026-07-09 19:23:21 -07:00

README.md

fix(release): harden plugin package preflight

2026-06-15 14:32:59 +08:00

README.md

@openclaw/llama-cpp-provider

Official llama.cpp embedding provider for OpenClaw.

This plugin runs local GGUF embedding models through node-llama-cpp.

Install

openclaw plugins install @openclaw/llama-cpp-provider

Restart the Gateway after installing or updating the plugin. Use Node 24 for native installs and updates.

Configure

Set agents.defaults.memorySearch.provider to local. By default, the plugin downloads and uses the EmbeddingGemma GGUF model. Configure agents.defaults.memorySearch.local.modelPath to use another local path, Hugging Face model URI, or HTTPS model URL.

Package

Plugin id: llama-cpp
Package: @openclaw/llama-cpp-provider
Minimum OpenClaw host: 2026.6.2