A high-accuracy web search API optimized for AI agents to perform deep research with rich excerpts and citations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install parallel-ai
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install parallel-ai using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Parallel.ai Search & Research?
Parallel.ai provides a specialized search infrastructure designed specifically for AI agents, outperforming traditional search engines in research benchmarks. By integrating this into Openclaw Skills, developers can equip their agents with the ability to perform fact-checking, company research, and complex multi-hop reasoning with evidence-based outputs.
This skill bridges the gap between static LLM knowledge and the live web, providing structured data that is easy for agents to parse and synthesize. It is built to prioritize accuracy and detail, ensuring that the research conducted by your agents is grounded in high-quality web sources.
Parallel.ai Search & Research Use Cases
- Deep research requiring cross-referenced facts and citations
- Detailed company or individual profiling for business intelligence
- Real-time fact-checking and evidence gathering for content generation
- Executing complex queries that require multi-step reasoning and synthesis
How Parallel.ai Search & Research Works
- The AI agent triggers a research request using the Parallel.ai skill interface via specified triggers like parallel or deep search.
- The system selects an execution mode—one-shot, fast, or agentic—based on the query complexity and latency requirements.
- Parallel.ai crawls and indexes relevant web sources, extracting high-fidelity text excerpts instead of raw HTML.
- The skill returns a structured JSON response containing source URLs, titles, and usage statistics to the agent.
- The agent processes the retrieved data to provide an accurate, cited answer to the user.
Parallel.ai Search & Research Setup
First, install the necessary Python package within your environment:
pip install parallel-web
Configure your API key and use the Python SDK to initiate searches within your Openclaw Skills scripts:
from parallel import Parallel
client = Parallel(api_key="YOUR_KEY")
response = client.beta.search(
mode="one-shot",
max_results=10,
objective="your query"
)
Parallel.ai Search & Research Data Schema & Taxonomy
The skill returns a structured response object designed for easy consumption by AI models:
| Field | Description |
|---|---|
search_id |
A unique identifier for tracking the search session. |
results[] |
An array containing objects with url, title, excerpts, and publish_date. |
usage |
Metadata regarding API consumption and token usage stats. |
excerpts[] |
Relevant text snippets extracted specifically for their informational value. |
Parallel.ai Search & Research Advanced Features
- Agentic Mode: Enables multi-hop research where the tool performs multiple steps to find answers to complex queries.
- High-Density Excerpts: Provides text snippets optimized for LLM context windows to reduce noise and token waste.
- Flexible Latency: Offers a Fast mode for quick lookups where cost and speed are prioritized over deep analysis.
- JSON Output Support: Includes a dedicated flag for structured data returns, making it ideal for automated pipelines.
SKILL.md
Loading
Related Openclaw Skills
markdown-new
Transform public web content into clean, LLM-ready Markdown for efficient AI data ingestion and processing.
Manus AI Agent
An autonomous AI agent skill that executes complex tasks through web browsing and tool usage via the Manus API.
clawdex
A high-performance CLI tool for executing and simulating token trades on the Solana blockchain via the Jupiter aggregator.
Kagi Summarizer
A high-performance AI tool that distills any URL or text into concise summaries or bulleted takeaways using the Kagi Universal Summarizer API.
Polymarket Prediction Market Tool
A comprehensive CLI tool for tracking Polymarket prediction markets, monitoring price momentum, and simulating trades via a local paper trading system.
Supabase
A powerful integration for querying Supabase projects and generating user analytics directly from your chat interface.
Featured*
