Memtrace Codebase Memory

v0.4.61Knowledge & Memorystable

Memtrace is a persistent memory layer for coding agents, built as a bi‑temporal structural knowledge graph over your codebase (AST‑driven symbols and relationships, plus temporal evolution and cross‑service API topology)

agent-memoryai-agentsbi-temporal-graphclaude-codecode-intelligence
Share:
170
Stars
0
Downloads
0
Weekly
0/5

What is Memtrace Codebase Memory?

Memtrace Codebase Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to memtrace is a persistent memory layer for coding agents, built as a bi‑temporal structural knowledge graph over your codebase (ast‑driven symbols and relationships, plus temporal evolution and cross‑s...

Memtrace is a persistent memory layer for coding agents, built as a bi‑temporal structural knowledge graph over your codebase (AST‑driven symbols and relationships, plus temporal evolution and cross‑service API topology)

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Memtrace is a persistent memory layer for coding agents, bui

Use Cases

Persistent memory for coding agents
AST-driven symbol tracking
Cross-service API topology
syncable-dev

Maintainer

LicenseNOASSERTION
Languagepython
Versionv0.4.61
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y memtrace

Manual Installation

npx -y memtrace

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Memtrace Codebase Memory

Memtrace provides a persistent, bi-temporal structural memory layer for AI coding agents by building a knowledge graph of AST-derived symbols, their relationships, and their full version history over your codebase. It exposes 25+ MCP tools covering semantic and exact code search, caller/callee relationship analysis, blast-radius impact analysis, dead code detection, cyclomatic complexity measurement, API topology mapping, and temporal evolution queries — all without any LLM calls for retrieval. It integrates automatically with Claude Code, Cursor, Codex, Windsurf, VS Code Copilot, Hermes, OpenCode, and Kiro.

Prerequisites

  • Node.js 18 or higher (LTS recommended)
  • Git installed and accessible in PATH (required for temporal/evolution analysis)
  • At least 8 GB RAM (16-32 GB recommended for large monorepos)
  • 5 GB free disk space for the graph database
  • An MCP-compatible coding agent: Claude Code, Cursor, Codex, Windsurf, VS Code, Hermes, OpenCode, or Kiro
1

Install Memtrace globally via npm

Installing globally makes the memtrace command available for the installer and for running the MCP server process.

npm install -g memtrace
2

Run the automatic multi-editor installer

The install command auto-detects supported editors on your system and configures MCP settings, skills files, and indexing guidance for each one.

memtrace install
3

Add to your MCP configuration manually

For editors not auto-detected (Cline, Roo Code, or custom setups), add this block to your MCP config file.

{
  "mcpServers": {
    "memtrace": {
      "command": "memtrace",
      "args": ["mcp"],
      "env": {}
    }
  }
}
4

Index your codebase

Ask your agent to index the project directory. Memtrace parses source files into AST symbols, resolves cross-file references, and builds the bi-temporal graph. This is the starting point for all subsequent queries.

5

(Optional) Enable live incremental indexing

Activate the watch_directory tool to keep the graph current as you make changes, so agents always work with up-to-date relationship data.

6

(Optional) Opt out of telemetry

Memtrace collects anonymous usage statistics by default. Disable this with the MEMTRACE_TELEMETRY environment variable.

export MEMTRACE_TELEMETRY=off

Memtrace Codebase Memory Examples

Client configuration (Claude Code)

MCP server configuration block for Claude Code or Claude Desktop.

{
  "mcpServers": {
    "memtrace": {
      "command": "memtrace",
      "args": ["mcp"],
      "env": {
        "MEMTRACE_TELEMETRY": "off"
      }
    }
  }
}

Prompts to try

Natural language queries that trigger Memtrace's MCP tools automatically through the agent's skill system.

- "Index this project so you can answer questions about the codebase."
- "Find where the UserRepository class is defined and show its dependencies."
- "Who calls the processPayment function? Show the full call chain."
- "If I change the AuthMiddleware, what else might break?"
- "Find all dead code — functions that are never called."
- "Show me the HTTP API endpoints across all services in this monorepo."

Troubleshooting Memtrace Codebase Memory

Indexing stalls or process runs out of memory

Large codebases need 16+ GB RAM. Try indexing a specific subdirectory first with the index_directory tool rather than the entire repo root.

Evolution and timeline tools return empty results

These tools require full Git history. If you cloned with --depth, re-clone with full history: 'git fetch --unshallow'. Also ensure the Git executable is in PATH.

After 'memtrace install', the agent does not see the MCP server

Restart your editor completely after install. If the editor is still not detected, add the server manually to your MCP config file and verify with 'memtrace mcp --help'.

Frequently Asked Questions about Memtrace Codebase Memory

What is Memtrace Codebase Memory?

Memtrace Codebase Memory is a Model Context Protocol (MCP) server that memtrace is a persistent memory layer for coding agents, built as a bi‑temporal structural knowledge graph over your codebase (ast‑driven symbols and relationships, plus temporal evolution and cross‑service api topology) It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Memtrace Codebase Memory?

Install via npm with the command: npx -y memtrace. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Memtrace Codebase Memory?

Memtrace Codebase Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Memtrace Codebase Memory free to use?

Yes, Memtrace Codebase Memory is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "memtrace": { "command": "npx", "args": ["-y", "memtrace"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Memtrace Codebase Memory?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides