浏览器

perplexity-toolkit

试用

Automate Perplexity AI search — batch, extract, aggregate, verify.

它能做什么

Automate Perplexity AI search — batch, extract, aggregate, verify.

技能文档

perplexity-toolkit

Automate Perplexity AI search via browser control — search, extract, batch, and analyze.

When to Use

  • Batch search hundreds of queries with resume support
  • Extract all cited sources from Perplexity results
  • Aggregate and deduplicate sources across multiple searches
  • Research tasks that need Perplexity's Deep Research or Model Council modes

Quick Start

git clone https://github.com/mfang0126/perplexity-toolkit.git
cd perplexity-toolkit
pip install -e .

CLI

perplexity search "query"                    # Standard search
perplexity search "query" --mode deep        # Deep research
perplexity search "query" --mode council     # Model council
perplexity batch queries.txt                 # Batch from file
perplexity aggregate results/ --output report.md
perplexity history                           # View search history

4 Search Modes

ModeWhat It Does
StandardQuick search with citations
Deep ResearchMulti-step, thorough investigation
Model CouncilMultiple models debate the answer
Step-by-stepLearning-oriented breakdown

Requirements

  • Python 3.10+
  • Playwright (browser automation)
  • Perplexity account (free tier works)

相关技能

Download and save Perplexity.ai conversations as individual Markdown files. One thread = one .md file. Processes threads sequentially. Supports single thread, URL lists, or full history export. Triggers on "download perplexity thread", "export perplexity history", "save all perplexity threads", or any request to capture Perplexity conversations.

Perplexity Sonar search and answer generation through AIsa. Use when the task is specifically to call Perplexity Sonar, Sonar Pro, Sonar Reasoning Pro, or So...

作者 baofeng-tech

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking...

作者 Nicolas Kleiber15 次安装1 星标

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

use for adaptive deep research, broad but accurate information gathering, literature review, github and project due diligence, source graph investigation, ci...

17 次安装