vrr/openclaw
2
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-08-01 11:06:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 16
openclaw/extensions/llama-cpp
History
Exact
Vincent Koc e96b9d2cd0
improve(ui): verify llama.cpp model setup
2026-07-30 23:41:58 +08:00
..
src feat(system-agent): constrain planner JSON output at generation time (#113482) 2026-07-24 21:00:28 -07:00
index.test.ts fix(agents): project llama.cpp-safe tool schemas (#115598) 2026-07-29 01:33:32 -04:00
index.ts fix(agents): project llama.cpp-safe tool schemas (#115598) 2026-07-29 01:33:32 -04:00
openclaw.plugin.json feat(llama-cpp): gate Gemma default by RAM (#109585) 2026-07-16 22:17:57 -07:00
package.json chore: update dependencies across workspace (#115677) 2026-07-29 05:16:42 -04:00
README.md improve(ui): verify llama.cpp model setup 2026-07-30 23:41:58 +08:00

README.md

@openclaw/llama-cpp-provider

Official llama.cpp text-inference and embedding provider for OpenClaw.

This plugin runs local GGUF chat and embedding models in-process 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 text inference

Choose llama.cpp during onboarding. After explicit consent, OpenClaw downloads Gemma 4 E4B IT Q4_K_M (approximately 5.0 GB) as the default. The bundled download is offered only on machines with at least 16 GiB of RAM. Discovery never downloads a model.

On smaller machines, use Ollama or LM Studio with a smaller model, use a cloud provider, or configure any custom GGUF through params.modelPath. The 16 GiB gate applies only to OpenClaw's bundled default download; custom GGUF models remain available on any machine.

See the llama.cpp provider guide for custom GGUF model configuration and hardware guidance.

Configure embeddings

Set memory.search.provider to local. By default, the plugin downloads and uses the EmbeddingGemma GGUF model. Configure memory.search.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