A privacy-obsessed deep research assistant that performs multi-round web searches and synthesizes cited reports using local SearXNG instances.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install privatedeepsearch-melt
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install privatedeepsearch-melt using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
privatedeepsearch-melt, also known as melt, is a specialized research assistant designed for users who demand absolute privacy and data sovereignty. Unlike mainstream AI search tools that log every query and build consumer profiles, melt functions as a local research engine that forgets every interaction the moment the task is finished. It is a robust addition to the ecosystem of Openclaw Skills, allowing users to perform deep web analysis without leaving a digital footprint.
Powered by SearXNG, melt aggregates data from engines like DuckDuckGo, Brave, and Startpage while strictly blocking Google and Bing. It offers a sophisticated multi-round research workflow that mimics the depth of platforms like Perplexity, but operates entirely on your local machine. This architecture ensures that your research queries remain private, encrypted, and beyond the reach of Big Tech data brokers.
To deploy this skill, ensure you have Docker and Docker Compose installed. Use the following commands to initialize the environment:
# Run the auto-setup script
./setup.sh
# Or start the containers manually
cd docker && docker-compose up -d
Once the local server is running at http://localhost:8888, install the skill into your agent framework:
cp -r skills/* ~/.clawdbot/skills/
# Or use the hub
clawdhub install privatedeepsearch-melt
| Component | Description | Path |
|---|---|---|
| Docker Configuration | Defines the SearXNG deployment and networking | /docker/docker-compose.yml |
| Engine Settings | Configures which search engines are trusted or blocked | /docker/searxng/settings.yml |
| Deep Research Logic | Contains the iterative scraping and synthesis algorithms | /skills/deep-research/ |
| Privacy Documentation | Technical details on the zero-log architecture | /docs/PRIVACY.md |
Loading
A secure, VPN-mandated search skill using local SearXNG for multi-iteration private research without tracking or rate limits.

A technical reference and workflow guide for implementing programmatic WhatsApp messaging through the Meta Cloud API.

A persistent learning framework that captures errors, corrections, and best practices to enable continuous improvement for AI coding agents.

A sophisticated multi-agent system designed for deep self-exploration through conversational coaching, personality profiling, and structured session synthesis.

An automated database tracking the latest state-of-the-art AI models across LLM, image, video, and audio categories with daily updates.

A daily book oracle skill that delivers uplifting book recommendations and poetic fortunes to inspire your day.








































