clawfinger-gateway

Run a local ASR-LLM-TTS pipeline for AI-assisted calls.

3|1|Updated Feb 22, 2026
One-click install
npx skills add https://github.com/Trac-Systems/clawfinger-gateway --skill clawfinger-gateway
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: clawfinger-gateway
Source: https://github.com/Trac-Systems/clawfinger-gateway/tree/main
Command: npx skills add https://github.com/Trac-Systems/clawfinger-gateway --skill clawfinger-gateway

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Clawfinger Gateway provides a local, cloud-free pipeline that orchestrates ASR, LLM, and TTS for AI-assisted calls, enabling robust privacy and low latency on macOS and Linux.

Core Features & Use Cases

  • On-device gateway that coordinates ASR, LLM, and TTS for live calls, with a UI dashboard and agent interface.
  • OpenClaw integration support via dedicated plugin bridges, agent takeover, and observation tools.
  • Instruction management and per-session history, plus optional caller filtering and persistent caller histories.

Quick Start

Install, configure, and start the gateway to run the local ASR → LLM → TTS pipeline with optional OpenClaw integration.

Frequently Asked Questions about clawfinger-gateway

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a local ASR LLM TTS pipeline for AI-assisted calls?

You can run a local ASR LLM TTS pipeline using the Clawfinger Gateway, which orchestrates on-device speech recognition, language model processing, and text-to-speech for live AI-assisted calls without cloud dependencies.

Does the on-device gateway support macOS and Linux deployments?

Yes, the on-device gateway supports macOS and Linux deployments, providing a cloud-free environment that ensures robust privacy and low latency for local ASR, LLM, and TTS operations.

Can I control the ASR LLM TTS gateway via WebSocket or REST API?

Yes, you can control the ASR LLM TTS gateway via its WebSocket and REST API surface, which enables runtime management alongside the provided UI dashboard and agent interface for live operations.

How do I configure per-session prompts and caller histories for AI calls?

You configure per-session prompts and persistent caller histories using the gateway's on-disk configuration and instruction management features, which also support optional caller filtering for AI-assisted calls.

What is OpenClaw integration for a local TTS gateway?

OpenClaw integration connects your on-device pipeline via dedicated plugin bridges, enabling agent takeover and observation tools to enhance live AI call management within the local gateway.

Why use an on-device ASR and TTS gateway instead of cloud-based services?

You use an on-device ASR and TTS gateway to ensure robust privacy and low latency for AI-assisted calls, avoiding cloud dependencies while maintaining full local control over your audio processing pipeline.