$ loading_
Offline code retrieval and structural analysis tools for AI agents with fewer tokens.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "CogniRepo" MCP server from askskill: Run: claude mcp add 'io-github-ashlesh-t-cognirepo' -- uvx cognirepo
Use CogniRepo on this repository to find payment-related functions, list key definitions and call chains, and identify the most likely entry file.
Returns code locations related to payment, major call relationships, and likely entry points for fast codebase understanding.
Use CogniRepo to retrieve the files and symbols most relevant to a user login error, then prepare only the necessary context for the next analysis step to minimize token usage.
Produces a compact set of relevant code context and retrieval results, reducing irrelevant content for downstream model analysis.
Using CogniRepo's AST and retrieval capabilities, find the functions, classes, and files related to log formatting and suggest the best places to modify.
Provides related symbols, their files, and recommended change points to help developers modify code faster.
Developers or researchers can use it for offline retrieval in large repositories, combining call graphs and AST to locate key modules and dependencies faster. This reduces time spent manually browsing files.
When an AI agent needs to analyze or modify code, this tool can first narrow down the most relevant context. One of its stated goals is to reduce token usage and improve efficiency on code tasks.
It fits teams that require local processing or offline operation, enabling code search and structural analysis without relying on online services. This is especially useful in constrained engineering environments.
It is an MCP tool that provides 34 tools for code retrieval and structural analysis for AI agents. The description says it combines FAISS, call graphs, AST, and BM25.
The original description explicitly says Offline, so it clearly emphasizes offline usage. For specific runtime details and limitations, see the source repository.
From the description, it does more than plain text search by combining FAISS, BM25, call graphs, and AST. In other words, it is geared toward semantic retrieval and structured code analysis for AI agents.
Search and navigate multiple code repositories with natural language understanding.
Query and understand large codebases with a fast knowledge graph for AI agents.
Help AI agents search, understand, and operate on codebases with a content-addressed graph.
Local hybrid search and SQL aggregation for code agents.
Gives AI coding agents a structural map of your repository fast.
Lets AI agents search codebases, locate files, and read files fast.