whereismyai
Codebase Memory MCP
Codebase Memory MCP is a code intelligence MCP server that indexes codebases into a persistent knowledge graph for AI coding agents, offering sub-millisecond query performance.
This MCP server indexes entire codebases into a persistent knowledge graph to improve AI coding agent performance. It utilizes tree-sitter AST analysis for parsing 162 languages, combined with Hybrid LSP semantic type resolution for specific languages like Python, TypeScript, and Go. The tool produces a structured graph containing functions, classes, call chains, and HTTP routes to replace traditional file-by-file exploration. It operates locally as a single native executable, requiring no external APIs, language runtimes, or hosted services. Users can explore this data through a built-in 3D graph visualization interface accessible at localhost.
Codebase Memory MCP at a glance
Key features
- Indexes repositories into persistent knowledge graphs
- Supports 162 languages via tree-sitter AST analysis
- Provides Hybrid LSP semantic type resolution
- Enables 3D graph visualization of code structure
- Includes 17 specific MCP tools for code exploration
- Delivers sub-millisecond structural query responses
- Operates via a native executable with no dependencies
Use it for
- Analyzing architectural impacts across codebases
- Detecting dead code via cross-service linking
- Managing architectural decision records
- Tracing function call chains and HTTP routes
Companion to
Tools whose articles name Codebase Memory MCP as a companion, each with its job for them.
Alternatives to Codebase Memory MCP
- Memory MCP server — Simple local memory that carries facts across chats
- jCodeMunch MCP — Cuts AI code-reading token costs by over 95 percent via tree-sitter symbol indexing.
- ContextMCP — Maintains fresh, accurate context for AI agents using AST-aware chunking.
- AI Memory — Shared memory for coding agents that works across machines and team members.
- CodeGraph — It eliminates file crawling, reducing AI agent tool calls by 88% and cutting costs.
- CodeGraphContext — Turns codebases into interactive knowledge graphs for AI assistants.
- IAI Memory Engine — Provides persistent, local, and encrypted memory for AI agents without APIs.
- Axiomcodegraph — Resolves calls from types rather than syntax for higher accuracy.
- Ctxfw — Reduces AI context token mass while preserving code structure and dependencies.
- CocoIndex — Maintains fresh context for AI agents with minimal incremental processing.
- CodeSight — Reduces AI token usage significantly and maps projects instantly.
- Coding Tools MCP — Turns any chat app into a coding agent with strict workspace safety boundaries.
All Codebase Memory MCP alternatives