ai-autodev

v0.38.0 suspicious
4.0
Medium Risk

Multi-agent orchestrator with tournament-based self-refinement for Claude Code, Cursor, and any LLM-assisted IDE

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package shows minimal risk in terms of network, shell, obfuscation, and credential handling. However, the absence of repository and author details raises suspicion about its origin and legitimacy.

  • missing repository details
  • missing author information
Per-check LLM notes
  • Network: No network calls detected, which is normal unless the package requires internet access for its functionality.
  • Shell: No shell execution patterns detected, indicating no direct system command execution from the package.
  • Obfuscation: No obfuscation patterns detected, indicating low risk.
  • Credentials: No credential harvesting patterns detected, indicating low risk.
  • Metadata: The missing repository and author details raise concerns about the legitimacy of the package.

📦 Package Quality Overall: Low (3.6/10)

○ Low Test Suite 1.0

No test suite detected

  • No test files or test-runner configuration detected
◈ Medium Documentation 7.0

Some documentation present

  • Documentation URL: "Documentation" -> https://github.com/mohamedameen/autodev#readme
  • Detailed PyPI description (46572 chars)
○ Low Contributing Guide 4.0

No contributing guide or governance files found

  • Development Status classifier >= Beta
◈ Medium Type Annotations 5.0

Partial type annotation coverage

  • Type checker (mypy / pyright / pytype) referenced in project
○ Low Multiple Contributors 1.0

Could not retrieve contributor data from GitHub

  • GitHub API error: 404

🔬 Heuristic Checks

✓ Outbound Network Calls

No suspicious network call patterns found

✓ Code Obfuscation

No obfuscation patterns detected

✓ Shell / Subprocess Execution

No shell execution patterns detected

✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

Email domain looks legitimate: example.com>

✓ Suspicious Page Links

All external links appear legitimate

⚠ Git Repository History score 3.0

Repository not found (deleted or private)

  • Repository not found (deleted or private)
⚠ Maintainer History score 4.0

2 maintainer concern(s) found

  • Author name is missing or very short
  • Author "" appears to have only 1 package on PyPI (new or inactive account)
✓ Known CVE Vulnerabilities

No known vulnerabilities found in OSV database.

💡 AI App Starter Prompt

Use this prompt to build a project with ai-autodev 
Create a mini-application named 'AutoDevTournament' that leverages the 'ai-autodev' package to orchestrate a coding challenge between multiple AI agents. This application will serve as an interactive platform where users can select different AI agents (such as Claude Code, Cursor, and others) to compete in solving coding problems. The goal of the application is to demonstrate the capabilities of these AI agents and provide insights into their strengths and weaknesses through tournament-style competitions.

The application should include the following core functionalities:
1. User Interface: A simple, intuitive interface where users can choose the AI agents they want to participate in the tournament and the type of coding problem they wish to solve (e.g., sorting algorithms, data structures).
2. Problem Generator: An automated system that generates coding problems based on user input or predefined categories.
3. Agent Selection: Users should be able to select from a list of available AI agents that support the 'ai-autodev' package. Each agent has its own unique approach to solving problems.
4. Tournament Execution: Once the agents and problem are selected, the application should run a series of tests where each agent attempts to solve the problem. The results should be compared based on accuracy, efficiency, and code quality.
5. Result Analysis: After the tournament, the application should provide a detailed analysis of each agent's performance, highlighting key metrics such as execution time, lines of code, and correctness of the solution.
6. Self-Refinement: Utilize the tournament results to allow the AI agents to learn and improve their strategies over time. This feature should be optional but available for advanced users who want to see how continuous learning impacts performance.

To utilize the 'ai-autodev' package effectively, follow these steps:
1. Initialize the application by importing necessary modules from 'ai-autodev'.
2. Set up the tournament framework using the provided classes and functions within the package to manage the competition flow.
3. Integrate the problem generator with the tournament setup to ensure dynamic challenges.
4. Implement the agent selection process, allowing for easy addition or removal of supported AI agents.
5. Use the evaluation tools provided by 'ai-autodev' to assess the solutions generated by each agent during the tournament.
6. Finally, implement the self-refinement process based on tournament outcomes, leveraging the tournament-based self-improvement features of 'ai-autodev'.

This project aims to showcase the versatility and competitive edge of various AI agents in a controlled, engaging environment, providing valuable insights for developers and enthusiasts alike.