QRev is an open-source, AI-first alternative to Salesforce, designed for scaling sales organizations. It aims to provide a modern, customizable CRM experience powered by AI agents, targeting businesses seeking a more flexible and intelligent sales platform than traditional solutions.

How It Works

QRev utilizes a "superagent" approach, where a central AI agent (Qai) coordinates internal digital workers based on user roles and permissions. This contrasts with mimicking real-world sales roles directly. The architecture comprises a client app (TypeScript), an app server (Node.js with MongoDB), and an AI server, leveraging Langchain for LLM tooling and ChromaDB for vector storage.

Quick Start & Requirements

• Installation: Clone the repository, navigate to the server directory, install dependencies (npm ci), configure .env files with JWT secrets and API tokens, and start the server (npm start). The client setup involves navigating to the client directory, installing dependencies (npm install), configuring .env with Google Client ID and API URLs, and running the client (npm start).
• Prerequisites: Node.js (>=18.18.0), MongoDB (>=5.x), Git, and an editor (e.g., VS Code). NVM is recommended for Node.js version management.
• Resources: Local setup requires installing Node.js and MongoDB. Integration setup requires obtaining credentials for specific services.
• Links: Website, Community Slack

Highlighted Details

• AI agents as a foundational element for sales operations.
• Tech stack includes TypeScript, Node.js, MongoDB, ChromaDB, SQLite, and Langchain.
• Supports user-uploaded CSV files for campaign generation.

Maintenance & Community

The project is under active development, with regular updates planned. A community Slack channel is available for contributions and discussions.

Licensing & Compatibility

The repository does not explicitly state a license in the provided README.

Limitations & Caveats

QRev is in early development, and the README explicitly states it is under active development, encouraging community contributions to shape its agentic foundation. Specific details on integrations are deferred to the Server README.