mirror of https://github.com/openclaw/openclaw.git synced 2026-08-02 18:01:35 +00:00

Files

Peter Steinberger f6131a4fbf build(deps): remove npm shrinkwrap; mirror pnpm lock into transient package locks (#114006 )

* build(deps): remove npm shrinkwrap; mirror pnpm lock into transient package locks

npm 12 removed shrinkwrap (command + tarball/root loading). Delete all 82
committed npm-shrinkwrap.json files and stop publishing lockfiles; keep
pnpm-lock.yaml as the single reviewed dependency boundary. The generator
becomes scripts/generate-npm-package-lock.mjs and feeds plugin bundling via
a transient package-lock.json + npm ci (works on npm 11 and 12). Tarball
validation treats the published 2026.7.2 beta train as a shrinkwrap
transition; self-update npm detection now uses install topology instead of
the shipped shrinkwrap.

* fix(deps): repair lint, deadcode, and test-type lanes for the npm 12 migration

- sort integrity comparisons with an explicit comparator (oxlint)
- keep resolveBunGlobalNodeModules module-local (knip unused-export gate)
- model npm pack --json as npm<=11 array / npm 12 name-keyed object
- default calver destructuring in the tarball test fixture

2026-07-26 01:29:55 -04:00

src

feat(system-agent): constrain planner JSON output at generation time (#113482 )

2026-07-24 21:00:28 -07:00

index.test.ts

feat(llama-cpp): in-process local GGUF text inference provider (#109444 )

2026-07-16 18:53:55 -07:00

index.ts

feat(llama-cpp): gate Gemma default by RAM (#109585 )

2026-07-16 22:17:57 -07:00

openclaw.plugin.json

feat(llama-cpp): gate Gemma default by RAM (#109585 )

2026-07-16 22:17:57 -07:00

package.json

feat(llama-cpp): in-process local GGUF text inference provider (#109444 )

2026-07-16 18:53:55 -07:00

README.md

refactor(config): config-surface reduction tranche 3 — product consolidations (review request) (#111527 )

2026-07-21 20:28:43 -07:00

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 Local model (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