h-codex is a semantic code search tool that enables intelligent, cross-repository context retrieval. It benefits developers and operations teams by improving code navigation and knowledge sharing. The tool connects to various codebases and integrates with vector databases for efficient semantic search.
git clone https://github.com/hpbyte/h-codex.gith-codex is a semantic code search tool designed for developers and operations teams who need intelligent context retrieval across multiple repositories. It uses Abstract Syntax Tree (AST) based chunking to parse code optimally, then creates semantic embeddings using OpenAI's text-embedding-3-small model and stores them in PostgreSQL with pgvector for efficient similarity search. The tool supports TypeScript and JavaScript with extensibility for other languages, and integrates seamlessly with AI coding assistants through the Model Context Protocol (MCP). h-codex helps teams improve code navigation, reduce knowledge silos, and accelerate development by making it easier to find relevant code context across projects.
Install h-codex via npm and configure it in Claude Desktop by editing claude_mcp_settings.json with your LLM API key and PostgreSQL connection string. Start a PostgreSQL database with pgvector using Docker, run database migrations with pnpm run db:migrate, and then start the development server. h-codex will then index your codebase and make semantic search available through your AI assistant.
Finding relevant code patterns and implementations across multiple repositories
Onboarding new team members by enabling context-aware code exploration
Improving code reusability by discovering similar implementations
Accelerating debugging by locating related code and error patterns across projects
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/hpbyte/h-codexCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Search for all functions related to user authentication in the [COMPANY] codebase, including those in [REPOSITORY_1] and [REPOSITORY_2]. Provide a summary of each function's purpose and parameters, and highlight any security considerations.
# User Authentication Functions in [COMPANY] Codebase ## Repository: [REPOSITORY_1] ### Function: `authenticateUser` - **Purpose**: Validates user credentials against the database. - **Parameters**: `username (string)`, `password (string)` - **Security Considerations**: Uses bcrypt for password hashing. Ensure input sanitization to prevent SQL injection. ### Function: `generateAuthToken` - **Purpose**: Generates a JWT token for authenticated users. - **Parameters**: `userId (string)`, `expiry (number)` - **Security Considerations**: Token should be signed with a secure secret key. ## Repository: [REPOSITORY_2] ### Function: `validateSession` - **Purpose**: Checks if a user session is still valid. - **Parameters**: `sessionId (string)` - **Security Considerations**: Session validation should include checks for session expiration and IP address changes.
AI sales agent for lead generation and follow-up
AI-assisted web application security testing
Get more done every day with Microsoft Teams – powered by AI
Automate your spreadsheet tasks with AI power
Agentic AI Workflow platform
Connected workspace for docs, wikis, and projects
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan