npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@2501-ai/cli

v0.3.20

Published

[![npm version](https://img.shields.io/npm/v/@2501-ai/cli.svg)](https://www.npmjs.com/package/@2501-ai/cli) [![HumanEval Score](https://img.shields.io/badge/HumanEval-96.95%25-brightgreen.svg)](https://www.2501.ai/research/full-humaneval-benchmark) [![Lic

Downloads

2,799

Readme

2501 CLI 🤖

npm version HumanEval Score License Discord

Your AI-powered autonomous agent that codes, interacts with your infrastructure and development workflows.

Whether you're debugging production issues, automating DevOps tasks, or seeking coding assistance, 2501 CLI brings the power of multiple specialized autonomous agents directly to your terminal.

2501.ai

🚀 Getting Started

  1. Install the CLI:
npm install -g @2501-ai/cli
  1. Set up your API key:
@2501 set api_key YOUR_API_KEY
  1. Supercharge your terminal:
@2501 Implement authentication in my express app

🤔 Why 2501?

  • 🎯 Unmatched Accuracy: 96.95% success rate on HumanEval, setting a new industry standard. Check out our benchmark for more details
  • 🧠 Multi-Model Intelligence: Unlike single-model solutions, 2501 leverages multiple specialized models
  • 🔍 Context-Aware: Understands your project structure and coding patterns
  • Self-Validating: Eliminates hallucinations through multi-model verification
  • Fast & Efficient - Get answers directly in your terminal
  • 🛠️ Workspace Aware - Understands your project context

🧠 How It Works

At the heart of 2501 is an orchestration of multiple of the top-performing models on the market today. Our approach, referenced as MoM (or Mixture of Models) going forward, is designed to maximize the successful execution of coding projects derived from natural language instructions.

With no one-size-fits-all model available, output quality is highly task-dependent. Our approach is to decompose any complex software development requirements into bite-sized tasks that can then be assigned to the most suitable model for resolution.

That’s precisely why the MoM approach shines and 2501’s autonomy does not stop here. On top of that, we continually evaluate the resolution of each task with a second model to improve or fix potential hallucinations.

📊 Comparison with Other Solutions

| Feature | 2501 | GitHub Copilot | Other AI Assistants | | -------------------- | ------ | ------------------------------------------------- | --------------------------------------------------------- | | HumanEval Score | 96.95% | ~48.1% | ~90% | | Multi-Model Approach | ✅ | ❌ | ❌ | | Self-Validation | ✅ | ❌ | ❌ | | Workspace Awareness | ✅ | ✅ | Varies | | Terminal Integration | ✅ | ❌ | Varies |

💻 System Requirements

  • Node.js 16.x or higher

Commands

Set Command

  • Description: Set configuration values.
  • Usage: @2501 set <key> <value>
    • api_key: Set the API key retrieved from the 2501 desktop app.

Config Command

  • Description: Fetches available agentic configurations from the API.
  • Usage: @2501 config

Query Command

  • Description: Execute a query using the specified agent.
  • Common usage: @2501 Implement authentication in my express app
    • This will execute the query using the agent assigned to the current workspace.
  • Custom Usage: @2501 <query> [--workspace <path>] [--agentId <id>]

Init Command

  • Description: Initializes a new agent.
  • Usage: @2501 init [--name <name>] [--workspace <path>] [--config <configKey>]

Agents Command

  • Description: List agents in the current workspace or all agents on the machine.
  • Usage: @2501 agents [--workspace <path>] [--all] [--flush]

Jobs Command

  • Description: Fetch jobs from API.
  • Usage: @2501 jobs [--workspace <path>] [--subscribe] [--listen]
    • --workspace <path>: Specify a different workspace path.
    • --subscribe: Subscribe every minute to the API for new jobs on the current workspace.
    • --unsubscribe: Unsubscribe the current workspace for new jobs.
    • --listen: Listen for new jobs from the API and execute them.

Remote Execution

Execute commands on remote servers using the --remote-exec option. Supports multiple authentication methods:

SSH Authentication Methods

# Basic connection
@2501 init --remote-exec [email protected]:22

# With private key authentication (works with PEM or RSA keys (default ~/.ssh/id_rsa))
@2501 init --remote-exec [email protected]:22 --remote-private-key $(cat ./some.pem)

# With password authentication
@2501 init --remote-exec [email protected]:22 --remote-exec-password yourpassword

# Specify connection type (ssh is default)
@2501 init --remote-exec [email protected]:22 --remote-exec-type ssh

WinRM Authentication (Windows)

# WinRM connection with password
@2501 init --remote-exec [email protected]:5985 --remote-exec-type winrm --remote-exec-password yourpassword

Options

  • --remote-exec <connection>: Enable remote execution (user@host:port)
  • --remote-private-key <privateKey>: Path to private key for remote execution
  • --remote-exec-type <type>: Type of remote execution: ssh or winrm (defaults to ssh)
  • --remote-exec-password <password>: Password for remote execution

🤝 Contributing

We welcome contributions! Have questions or suggestions? Reach out to us:

🔒 Security

Found a security issue? Please email [email protected]

📄 License

This project is licensed under the ISC License - see the LICENSE file for details.