Quick Start Guide

Welcome to Unoplat Code Confluence - Your Gateway to Code Understanding!

Prerequisites

Before you begin, ensure you have the following tool installed:

Setting Up Code Confluence

Follow these steps to set up Code Confluence:

1. Create Project Directory and Download Configuration:

   mkdir -p code-confluence && cd code-confluence
   
   # Download Docker Compose file
   curl -O https://raw.githubusercontent.com/unoplat/unoplat-code-confluence/refs/heads/main/prod-docker-compose.yml

2. Launch Services:

   docker compose -f prod-docker-compose.yml up -d

3. Verify Deployment:

   docker compose -f prod-docker-compose.yml ps

Running the Application

1. Access the Web Interface

• Open your browser and go to http://localhost:3000

2. Enter Your GitHub Personal Access Token (PAT)

• When prompted, enter a GitHub PAT with read access to the repositories you want to ingest.
• This is required for Code Confluence to clone and analyze your repositories.

3. Search for GitHub Repositories

• Press s or S (Shift + s) to open the search dialog.
• You can search through your personal, public, and open source repositories.

4. Ingest Repository

• In the Actions column, click on Ingest Repo for the repository you want to analyze.
• Code Confluence will automatically detect Python and TypeScript codebases as part of repository along with corresponding package manager metadata.

5. Configure Model Provider

After ingestion completes, configure your AI model provider to enable code intelligence features.

• Navigate to Settings > Model Providers in the application
• Code Confluence supports multiple AI model providers for code analysis and understanding

Recommended Configuration: OpenRouter with Grok

We recommend using OpenRouter with the x-ai/grok-code-fast-1 model, which we've tested extensively for optimal performance and efficiency.

Setup Steps:

1. Select OpenRouter from the Provider dropdown
2. Enter your OpenRouter API key in the API key field
3. Set the Model name to x-ai/grok-code-fast-1
4. Click Save Configuration

6. Repository Operations

After successfully ingesting your repository, you can perform various operations to manage your codebase. Navigate to Ingestion Management to access these operations.

Code Confluence provides three key repository operations:

• Generate Agents.md — Automatically generates comprehensive documentation for AI agents to understand your codebase
• Refresh Repository — Updates your ingested codebase to reflect the latest changes from the source repository
• Delete Repository — Removes the ingested repository and all associated data from Code Confluence

AGENTS.md

When you trigger the Generate Agents.md operation, you can monitor the progress in real-time. The workflow shows progress for each codebase individually, as well as overall progress when your repository contains multiple codebases. You can view agent events in real-time as actions are performed.

You can continue ingesting and generating AGENTS.md for multiple repositories in parallel until you reach the maximum tokens per second limit of your model provider.

The generated AGENTS.md provides structured documentation covering:

• Project Structure — Overview of your codebase organization
• Development Workflow — Development practices and patterns
• Business Logic — Core functionality and domain logic

7. Monitor Ingestion & Enable Developer Mode

• Navigate to Settings > Developer Mode, and toggle the switch on to unlock infrastructure tooling.
• Once enabled, you will see two new tools:

Workflow Orchestrator

• Access and manage automated workflows
• View execution logs and debug orchestration issues
• Monitor real-time workflow performance
• Click the "Workflow Orchestrator" button to open the Temporal workflow orchestrator dashboard.

Knowledge Graph

• Explore the knowledge graph, inspect entities and relationships, and debug data connections
• Click the "Knowledge Graph" button to open the Neo4j Browser directly
• When Neo4j Browser opens, you'll be prompted to log in with:

  Username: neo4j
  Password: password

• Once logged in, try this query to explore your code graph:

  MATCH (n)
  RETURN n
  LIMIT 25

Troubleshooting

Need assistance? We're here to help!

Support Options

1. GitHub Issues

   • Visit GitHub Issues to:
     • Report bugs or request features
     • Browse existing solutions
     • Get developer support

2. Community Support

   • Join our Discord Community to:
     • Connect with other users
     • Get real-time assistance