PatrickSys/codebase-context

Overview

A TypeScript tool that generates a structured map of a codebase, including architecture, coding conventions, and patterns. It uses semantic search to make the map discoverable for AI agents.

Best for

Best for
Developers who want to give AI agents a structured understanding of their codebase's architecture and conventions.

Use cases

• Onboarding AI agents to a new codebase by providing a structured context map
• Enabling semantic search across codebase architecture and conventions
• Standardizing codebase documentation for agent-assisted development

How to use

Install

npx -y codebase-context map

Tools exposed

• search_codebase
• get_team_patterns
• get_symbol_references
• get_memory
• get_codebase_metadata
• get_style_guide
• detect_circular_dependencies
• refresh_index
• get_indexing_status
• EMBEDDING_PROVIDER
• OPENAI_API_KEY
• CODEBASE_ROOT
• CODEBASE_CONTEXT_DEBUG
• EMBEDDING_MODEL
• CODEBASE_CONTEXT_HTTP
• CODEBASE_CONTEXT_PORT
• CODEBASE_CONTEXT_CONFIG_PATH

Tested with

Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, ChatGPT

Notes

A TypeScript tool that generates a structured map of a codebase, including architecture, coding conventions, and patterns. It uses semantic search to make the map discoverable for AI agents.

45 stars on GitHub. Last updated 2026-05-11.

Use cases

• Onboarding AI agents to a new codebase by providing a structured context map
• Enabling semantic search across codebase architecture and conventions
• Standardizing codebase documentation for agent-assisted development

Pros

• Semantic search makes codebase context easily discoverable
• Lightweight TypeScript implementation with low overhead
• Focuses on architecture and conventions, not just file listings

Cons

• Small community with only 45 stars, limited support
• Requires manual setup and maintenance of the context map
• May not scale well for very large or rapidly changing codebases

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.