$ loading_
Search code, extract symbols, map imports, and package repository context locally.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "CodeGraph Memory MCP Lite" yet — see the docs or source repo.
Search this research code repository for files related to the training workflow, and list the most likely entry files and config files by path.
A list of relevant file paths, highlighting likely training entry points and configuration locations.
Extract the Python classes and functions related to data loading in this repository, grouped by module.
A module-grouped list of classes, functions, or symbols to help quickly understand the code structure.
Analyze the import relationships around evaluation.py and assemble a repository context pack for code review.
An overview of import relationships plus a context pack summarizing repository information relevant to the target file.
When a developer or researcher inherits an unfamiliar repository, they can search key files, extract Python symbols, and inspect import relationships to build a fast understanding.
Before code review, debugging, or asking AI to analyze a repository, users can assemble repo context packs to gather relevant files and structural information.
In a complex Python project, users can use the import graph to inspect module dependencies and better understand call chains and project organization.
It is a local-first, MCP-style code memory tool for research repositories. Its known capabilities include file search, Python symbol extraction, import graph analysis, and repository context packing.
Based on the description, it explicitly supports Python symbol extraction, so it is at least designed for Python code structure analysis. For other language support, see the source repository.
The provided material does not include installation steps, runtime requirements, or API key details. For prerequisites, see the source repository.
Index codebases into Neo4j for analysis, dependency mapping, and impact assessment.
Build local codebase memory for AI agents with search and architecture insights.
Index repositories into a persistent graph for fast code search and understanding.
Build a project knowledge graph for code search, traversal, and Q&A.
Turn any LLM into a codebase expert with search, mapping, and security insights.
Build a knowledge graph from repos for Q&A and implementation planning.