glommer/codemogger

Score: 37.6 Rank #3324

Codemogger is a code indexing library and MCP server for AI coding agents

Overview

glommer/codemogger is a TypeScript MCP server licensed under MIT. Codemogger is a code indexing library and MCP server for AI coding agents

Ranked #3324 out of 25632 indexed tools.

Actively maintained with commits in the last week.

Ecosystem

TypeScript MIT

Signal Breakdown

Stars 268

Freshness 7d ago

Issue Health 0%

Contributors 5

Dependents 0

Forks 18

Description Good

License MIT

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Issue Health high impact

You have 5 open vs 0 closed issues — triaging stale issues improves health

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge

Markdown

[![AgentRank](https://agentrank-ai.com/api/badge/tool/glommer--codemogger)](https://agentrank-ai.com/tool/glommer--codemogger)

HTML

<a href="https://agentrank-ai.com/tool/glommer--codemogger"><img src="https://agentrank-ai.com/api/badge/tool/glommer--codemogger" alt="AgentRank"></a>

Details

Stars: 268
Forks: 18
Open Issues: 5
Closed Issues: 0
Contributors: 5
Dependents: —
Language: TypeScript
License: MIT
Last Commit: 7d ago

Matched Queries

"mcp server""mcp-server"

From the README

<p align="center">
  
</p>

# codemogger

Code indexing library for AI coding agents. Parses source code with tree-sitter, chunks it into semantic units (functions, structs, classes, impl blocks), embeds them locally, and stores everything in a single SQLite file with vector + full-text search.

No Docker, no server, no API keys. One `.db` file per codebase.

## Why

Coding agents need to understand codebases. They need to find where things are defined, discover how concepts are implemented across files, and navigate unfamiliar code quickly. This requires both keyword search (precise identifier lookup) and semantic search (natural language queries when you don't know the exact names).

As AI coding tools become more composable - agents calling agents, MCP servers plugging into different hosts - this capability needs to exist as a library that runs locally. No external servers, no API keys, no Docker containers. Just a function call that returns results.

codemogger is that library. Emb

Read full README on GitHub →

View on GitHub →

Are you the maintainer? Claim this listing