ai-researcher  by mshumer

AI agent for comprehensive research reports

created 1 year ago
932 stars

Top 40.1% on sourcepulse

GitHubView on GitHub
Project Summary

This project provides an AI agent designed to automate comprehensive research on any given topic, producing detailed, synthesized reports. It targets researchers, students, and professionals needing to quickly gather and organize information from the web. The primary benefit is the automation of a time-consuming research process, delivering a structured and consolidated output.

How It Works

The agent leverages Anthropic's Claude 3 models and SERPAPI for web searches. It breaks down a user-provided topic into manageable subtopics, conducts iterative searches and analysis for each, and generates individual reports. A "boss" persona is incorporated to refine these reports by identifying gaps and suggesting improvements, culminating in a final, comprehensive document. A recent addition includes a Gemini 1.5 Pro version for analyzing YouTube video content.

Quick Start & Requirements

  • Install/Run: Open the provided .ipynb notebook in Google Colab or a local Jupyter environment.
  • Prerequisites: Requires ANTHROPIC_API_KEY and SERP_API_KEY.
  • Setup: Replace placeholder API keys and run all cells. The report is saved as comprehensive_report.txt.
  • Links: Gemini_Youtube_Researcher.ipynb

Highlighted Details

  • Supports multiple rounds of search and analysis per subtopic.
  • Incorporates a "boss" persona for iterative report refinement.
  • Offers customization for model selection (e.g., "claude-3-haiku-20240307"), max_tokens, and temperature.
  • Includes a separate version for YouTube video analysis using Gemini 1.5 Pro.

Maintenance & Community

The project is maintained by Matt Shumer. Contributions are welcomed via GitHub issues or pull requests.

Licensing & Compatibility

  • License: MIT License.
  • Compatibility: Permissive license suitable for commercial use and integration with closed-source projects.

Limitations & Caveats

Report quality is dependent on the performance of Claude AI and SERPAPI search results. Execution time can be significant for complex topics. The tool is experimental and generated information should be verified.

Health Check
Last commit

1 year ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
7 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.