ClawHubCN
@openclaw

llama.cpp Provider

OpenClaw llama.cpp embedding provider plugin

Download plugin View Git source
Current version
v2026.7.1
code-pluginOfficialsource-linked

@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

Source and release

Source repository

openclaw/openclaw

Open repo

Source commit

2d2ddc43d0dcf71f31283d780f9fe9ff4cc04fe4

View commit

Install command

openclaw plugins install clawhub:@openclaw/llama-cpp-provider

Metadata

  • Package: @openclaw/llama-cpp-provider
  • Created: 2026/06/12
  • Updated: 2026/07/13
  • Executes code: No
  • Source tag: refs/tags/v2026.7.1

Compatibility

  • Built with OpenClaw: 2026.7.1
  • Plugin API range: >=2026.7.1
  • Tags: beta, latest
  • Files: 5