Getting Started
Start with simply signing up with Agiflow—it's free, so give it a spin.
Simple Workflow
Follow these four steps to start automating your development workflow with AI agents.
Sign Up & Create Project
Once you're in, create a "New Project" and click on "Start planning". This sets up your workspace and enables AI agents to understand your project context.
Create New Project
Add a new project to organize your tasks and workflows.
Connect Your AI Agent
Launch your AI agent via agent-cli. Connect to the Agiflow backend to sync tasks, or run in standalone mode for local development.
Run Tasks in Sandbox
Execute tasks safely in isolated sandbox environments. Run multiple concurrent tasks with real-time streaming to your dashboard. Each task runs independently while maintaining full visibility.
Task Dashboard
Implement user authentication
Add JWT-based authentication with login, signup, and password reset functionality
Fix responsive layout issues
Update CSS media queries and flexbox layouts for mobile compatibility
Set up database models
Create PostgreSQL schemas and models for users, projects, and tasks
Review & Iterate
Review completed work through the dashboard. Provide feedback via comments and re-run agents with conversation history to implement improvements seamlessly.
Implement user authentication
Acceptance Criteria
Add Comment
Comments (2)
I've completed the basic authentication flow. The login form and JWT implementation are working correctly. Ready for your review!
Thanks for the quick implementation! I've tested the login flow and it works great. Can you please add the password strength validation and remember me checkbox as mentioned in the acceptance criteria?
MCP Integration: 3-Step Setup
Connect your AI coding assistant to Agiflow in 3 simple steps: Select your tool, choose a connection method, and copy your configuration.
Select Your AI Coding Tool
Choose which AI coding assistant you want to configure for MCP connection
Select Connection Method
Choose how you want to connect to Agiflow's MCP servers
HTTP MCP + Marketplace
Use Agiflow HTTP MCP with Claude Code marketplace integration
Features:
- ✓Direct HTTP connection to Agiflow API
- ✓Automatic updates via marketplace
- ✓Simple configuration
- ✓Works with platform-tools
Requirements:
- →Claude Code installed
- →Internet connection
stdio MCP Proxy
Use @agiflowai/powertool as stdio MCP proxy
Features:
- ✓Works with all MCP-compatible tools
- ✓Fetches configs from Agiflow endpoint
- ✓More flexible configuration
- ✓Local proxy for enhanced control
Requirements:
- →platform-tools installed
- →@agiflowai/powertool package
Copy & Paste Configuration
Follow the detailed setup guide for your selected tool to get your configuration
What You'll Get:
- Your unique API key
- Ready-to-use configuration JSON
- Environment variables (if needed)
- Step-by-step instructions
After Setup:
- Restart your AI coding tool
- Verify MCP connection
- Start using Agiflow tools
- Create tasks from your editor
Ready to Connect Your Tool?
Select your AI coding assistant below to get started with detailed setup instructions and ready-to-use configurations.
Next Steps
Claude Code Setup
Detailed setup instructions for connecting Claude Code with HTTP MCP or stdio proxy.
Cursor Setup
Detailed setup instructions for connecting Cursor with stdio MCP proxy.
Spec + Task Management
Learn how Work Units solve AI session state loss with devInfo metadata.
Multi-Agent
Understand agent members, session management, and model routing.
Agent CLI
CLI tool for agent connections, session tracking, and model routing.
Need Help?
Having trouble getting started? Here are some resources to help you: