ClawHub
Code Pluginsource linkedVerified

llama.cpp Providerv2026.9.2

OpenClaw provider for managed and external llama.cpp servers

@openclaw/llama-cpp-provider·runtime llama-cpp·by @openclaw
openclaw plugins install clawhub:@openclaw/llama-cpp-provider
Latest release: v2026.9.2Download zip

Compatibility

Built With Open Claw Version
2026.9.2
Min Gateway Version
>=2026.6.2
Plugin Api Range
>=2026.9.2
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
ℹ
Credentials
The plugin probes host RAM, disk, platform, and GPU tooling to recommend a local model; that environment access is proportionate to selecting a runnable local inference server and is described as setup-time behavior.
ℹ
Install Mechanism
Managed setup can download and execute a pinned llama-server build plus GGUF models from GitHub and Hugging Face, but the README discloses this and the code uses HTTPS, expected hashes, archive limits, and explicit user confirmations before setup downloads.
✓
Instruction Scope
Runtime actions are scoped to llama.cpp setup, model discovery, local embedding support, and provider request compatibility; I found no unrelated agent instructions, hidden prompting, or broad local-data indexing behavior.
ℹ
Persistence & Privilege
It persists provider configuration, model cache files, a managed local-service command, and optional llama-server API-key auth profiles; these are expected for the provider and include cleanup/removal paths when switching auth modes.
✓
Purpose & Capability
The package purpose is to provide managed and external llama.cpp chat and embedding support, and the code matches that purpose by registering a provider, discovering models, downloading verified runtimes/models, and routing OpenAI-compatible requests.
Assessment
Install this only if you want OpenClaw to manage or connect to a llama.cpp server. Expect large model downloads, local disk use, a persistent OpenClaw-managed server configuration, and optional storage of an API key if you connect to a protected existing server.
✗
dist/index.js:407
Shell command execution detected (child_process).
✗
dist/index.js:1805
File appears to expose a hardcoded API secret or token.
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.

Verification

Tier
source linked
Scope
artifact only
Summary
Validated package structure and linked the release to source metadata.
Source
github.com/openclaw/openclaw
Commit
3928bad9badf
Tag
3928bad9badfcb6c7d140530435e806fb8092190
Provenance
No
Scan status
clean

Tags

beta
2026.7.2-beta.7
latest
2026.9.2

@openclaw/llama-cpp-provider

Official llama.cpp provider for managed and external OpenClaw model servers.

The llama-cpp provider either installs a pinned, integrity-verified llama-server under OpenClaw's localService supervisor or connects to a server that you already operate. Both choices use llama-cpp/<model> references and OpenClaw's normal OpenAI-compatible chat transport. Local embeddings require the managed choice.

Install

openclaw plugins install @openclaw/llama-cpp-provider

Restart the Gateway after installing or updating the plugin. Interactive setup shows Managed local server and Existing llama-server under one Local llama.cpp group.

Configure managed text inference

After explicit consent, OpenClaw installs the matching server build and downloads Gemma 4 E4B IT Q4_K_M (approximately 5.0 GB) plus EmbeddingGemma (approximately 0.3 GB). The default chat download is offered only on machines with at least 16 GiB of RAM.

When local memory search is configured and chat setup is unavailable or declined, OpenClaw offers a separate embedding-only setup. After explicit consent, it installs only the server and EmbeddingGemma. It leaves the current chat model unchanged. Move any llama.cpp chat routes and remove its configured chat model entries first. Remove an existing external server config before retrying embedding-only setup.

Custom GGUF models remain supported through params.modelPath. Rerun llama.cpp setup after changing the model so OpenClaw can verify the file and regenerate the managed router preset.

See the llama.cpp provider guide for platform requirements, custom GGUF configuration, diagnostics, and repair.

Connect to an existing server

Choose Existing llama-server during setup and enter the endpoint and optional API key. OpenClaw passively discovers single-model and router catalogs. It never installs, starts, stops, or reconfigures the external process.

See the llama.cpp provider guide for authentication, router behavior, manual configuration, and troubleshooting.

Configure embeddings

Set memory.search.provider to local. The plugin preserves the historical local embedding provider and index identity while serving requests through the managed server's /v1/embeddings endpoint.

Package

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