Intel Arrow Lake NPU Tools for Linux

An unofficial, community-maintained toolkit that makes the integrated Intel AI Boost NPU in Arrow Lake processors useful on Linux. It provides private semantic search, local speech transcription, screenshot OCR, hardware verification, and ten MCP tools that AI agents can call.

This project is not affiliated with, sponsored by, or endorsed by Intel Corporation. Intel, Intel Core, OpenVINO, and Intel AI Boost are trademarks of their respective owners.

Why this exists

Linux can expose an Arrow Lake NPU as /dev/accel/accel0, but applications still need Intel's Level Zero NPU user-mode driver, OpenVINO, compatible models, permissions, and integration code. This repository assembles those pieces into useful desktop and agent workflows.

The NPU is a good fit for efficient background inference. It does not replace a discrete GPU for model training, large language models, or image generation.

Related MCP server: local-mmcp

Features

• Speech to text: multilingual Whisper Base INT8 runs locally on the NPU.

• Screenshot OCR: select a region and copy recognized English or Arabic text.

• Private semantic search: index local documents, logs, and source code with Qwen3-Embedding 0.6B INT8, then retrieve passages by meaning.

• MCP server: Codex, Claude, Gemini CLI, AGY/Antigravity CLI, Hermes, Antigravity IDE, OpenCode, and other MCP clients can use all ten tools.

• Hardware diagnostics: report every OpenVINO device and confirm Intel(R) AI Boost is available.

• Reversible installation: user applications and models are isolated under ~/.local; the uninstaller deliberately preserves system drivers.

Supported hardware and software

The initial tested target is:

• Intel Arrow Lake integrated NPU 3720, PCI ID 8086:ad1d

• Intel Core Ultra 200-series desktop processors, including Core Ultra 9 285K

• Ubuntu 24.04 or an Ubuntu 24.04-compatible distribution

• Linux kernel 6.8 or newer with intel_vpu

• KDE Plasma Wayland for the included screenshot workflow

OpenVINO officially identifies Arrow Lake's NPU 3720 by PCI ID 0xAD1D. Other Intel NPU generations may work with code changes, but the bundled driver safety check intentionally refuses unknown PCI IDs.

Quick installation

git clone https://github.com/etreby/intel-arrow-lake-npu-tools.git
cd intel-arrow-lake-npu-tools
./install.sh --with-driver

--with-driver installs Intel's signed Ubuntu 24.04 NPU user-mode packages and firmware, adds the current user to render, creates an isolated Python environment, downloads the models from their official upstream locations, and installs the desktop and MCP tools.

Log out and back in after the first driver installation, then verify:

intel-npu-info

Expected output includes:

"NPU": "Intel(R) AI Boost"

If the driver is already installed, omit --with-driver:

./install.sh

To skip automatic MCP client registration:

./install.sh --without-mcp

The model download is approximately 800 MB in total, including Whisper, OCR, and the roughly 600 MB embedding model.

Semantic search in 30 seconds

intel-npu-search index ~/Projects/my-project
intel-npu-search search "Where is authentication configured?"
intel-npu-search status

Indexing is incremental and remains local. See the semantic-search guide for supported files, performance, privacy boundaries, and customization.

Desktop usage

Launch these applications from the desktop menu:

• Intel NPU Speech to Text: click Start, speak, then Stop and transcribe. The result is copied to the clipboard.

• Intel NPU Screenshot OCR: select a rectangular region. Recognized text is displayed and copied.

KDE shortcut declarations:

• Meta+Alt+S — Speech to Text

• Meta+Alt+O — Screenshot OCR

Meta is normally the Windows-logo key. Desktop environments may require one new login before discovering newly installed shortcuts.

AI agent and MCP usage

The local stdio MCP command is:

intel-npu-mcp

It exposes:

Example agent requests:

Use intel-npu-tools to transcribe ~/recording.m4a.
Use the NPU to OCR ~/Pictures/error.png.
Record my microphone for 15 seconds and transcribe it.
Read the text currently visible on my monitor.
Index ~/Projects/my-project, then find where authentication is configured.
Search my indexed documents for the Windows boot recovery procedure.

Manual Codex registration:

codex mcp add intel-npu-tools -- "$HOME/.local/bin/intel-npu-mcp"

Manual Claude Code registration:

claude mcp add --scope user intel-npu-tools -- "$HOME/.local/bin/intel-npu-mcp"

Manual Hermes registration:

hermes mcp add intel-npu-tools --command "$HOME/.local/bin/intel-npu-mcp"

Manual Gemini CLI registration:

gemini mcp add --scope user intel-npu-tools "$HOME/.local/bin/intel-npu-mcp"

AGY/Antigravity CLI reads global servers from ~/.gemini/config/mcp_config.json:

{
  "mcpServers": {
    "intel-npu-tools": {
      "command": "/home/YOUR_USER/.local/bin/intel-npu-mcp",
      "args": []
    }
  }
}

OpenCode reads global configuration from ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "intel-npu-tools": {
      "type": "local",
      "command": ["/home/YOUR_USER/.local/bin/intel-npu-mcp"],
      "enabled": true,
      "timeout": 60000
    }
  }
}

Any MCP client can use this stdio configuration:

{
  "mcpServers": {
    "intel-npu-tools": {
      "command": "/home/YOUR_USER/.local/bin/intel-npu-mcp",
      "args": []
    }
  }
}

How the NPU is utilized

Microphone/audio ──> Whisper Base INT8 ──> OpenVINO GenAI ──> Intel NPU
Screenshot/image ──> text detector + recognizer ──> OpenVINO ──> Intel NPU
                                      └──> Tesseract layout/language fallback
Local text ──> chunks ──> Qwen3 Embedding INT8 ──> Intel NPU ──> SQLite vectors
AI agent ──> local stdio MCP server ──> the same NPU pipelines

All inference targets NPU explicitly. The included tools do not silently redirect workloads to a discrete GPU. This allows an NVIDIA or Intel GPU to remain available for gaming, rendering, Ollama, or larger AI workloads.

Privacy

• No network server is started.

• MCP communication uses a local child process over stdin/stdout.

• Audio, screenshots, indexed text, and embeddings are processed and stored locally.

• Network access is needed only during installation to download software and models.

• Temporary recordings and screenshots are deleted after processing.

Documentation

• Semantic search, customization, and measured performance

• Troubleshooting and debugging

• Building agent skills

• Ready-to-copy local-knowledge skill

• Contributing

• Changelog

Troubleshooting

/dev/accel/accel0 is missing

lspci -nn | grep -i ad1d
lsmod | grep intel_vpu
journalctl -k -b | grep -i intel_vpu

Update the kernel/firmware for your distribution before replacing unrelated graphics drivers.

NPU exists but OpenVINO shows only CPU/GPU

groups
ls -l /dev/accel/accel0

The user must belong to render. Log out and back in after group changes.

Speech produces no text

Check the default PipeWire microphone:

pactl get-default-source
pw-record --rate 16000 --channels 1 /tmp/microphone-test.wav

OCR limitations

Intel's compact recognition model focuses on lowercase Latin letters and digits. Tesseract supplements it for punctuation, layout, English, and Arabic. Stylized fonts and very small text may remain imperfect.

For NPU compilation, semantic-search, and MCP diagnostics, use the complete debugging guide.

Development

python3 -m venv .venv
source .venv/bin/activate
pip install -e .
python -m compileall -q src

See CONTRIBUTING.md for contribution guidelines and proposed areas of work.

Uninstall

./uninstall.sh

The uninstaller removes user applications, models, and MCP registrations. It intentionally preserves system-level NPU firmware and drivers.

Upstream components and documentation

• Intel Linux NPU Driver

• OpenVINO NPU plugin

• OpenVINO GenAI on NPU

• Official MCP Python SDK

• OpenVINO Whisper Base INT8

• OpenVINO Qwen3 Embedding 0.6B INT8

• Open Model Zoo OCR tutorial

License

Project code is released under the MIT License. Downloaded drivers, models, runtimes, and trademarks remain under their respective upstream licenses. See THIRD_PARTY_NOTICES.md.