What makes claudemem different from standard grep?

Unlike grep, which looks for literal strings, claudemem uses vector embeddings and LLM summaries to find code based on meaning and intent, even if the exact keywords don't match.

What is LLM enrichment in v0.2.0?

Enrichment is a process where an LLM analyzes your code during indexing to create summaries of every file and function, allowing the search tool to understand the 'why' behind the code.

When should I use the 'navigation' use case?

The navigation use case is optimized for AI agents exploring a codebase; it prioritizes file and symbol summaries to give the agent a high-level map of the project structure.

Does claudemem require an internet connection?

While the vector search is local, the indexing and enrichment phases require an API key (such as OpenRouter) to connect to an LLM for generating embeddings and summaries.

claudemem Semantic Search

Name: claudemem Semantic Search
Author: MadAppGang

byMadAppGang

•

177

Developer Tools

Powers intelligent semantic code search and codebase discovery using LLM-enriched indexing and vector matching.

About

This skill integrates claudemem v0.2.0 to provide Claude with a deep, context-aware understanding of any codebase. By utilizing Tree-sitter for AST parsing and LLM-generated summaries of files and symbols, it moves beyond simple keyword matching to true semantic discovery. It allows developers and AI agents to find code based on purpose, behavior, and architectural role, offering specialized search modes like 'navigation' for exploration and 'fim' for completion to ensure the most relevant context is always available.

Key Features

Specialized search presets for AI navigation, developer queries, and code completion
Dual-matching architecture that searches both raw AST code chunks and semantic summaries
LLM-Enriched indexing that summarizes file purposes, exports, and symbol behaviors
177 GitHub stars
Role-specific AI instructions tailored for architects, developers, testers, and debuggers
Local vector storage via LanceDB for fast, privacy-focused semantic retrieval

Use Cases

Architectural discovery to map dependencies and entry points in a new codebase
Finding specific function implementations based on behavioral descriptions rather than names
Providing AI agents with optimized navigation context to prevent excessive file reading

About

Key Features

Specialized search presets for AI navigation, developer queries, and code completion
Dual-matching architecture that searches both raw AST code chunks and semantic summaries
LLM-Enriched indexing that summarizes file purposes, exports, and symbol behaviors
177 GitHub stars
Role-specific AI instructions tailored for architects, developers, testers, and debuggers
Local vector storage via LanceDB for fast, privacy-focused semantic retrieval

Use Cases

Architectural discovery to map dependencies and entry points in a new codebase
Finding specific function implementations based on behavioral descriptions rather than names
Providing AI agents with optimized navigation context to prevent excessive file reading