Enables agents to work with local hardware engineering context — registered repositories, imported PDFs and documents, and user-created system diagrams — through stdio tools for bounded source search and file reading, document text extraction and PDF page/crop rendering, and reading or drafting system architecture models. It runs entirely on local storage with no code index, hosted backend, or model provider routing, leaving the agent's own model, keys, and permissions intact.
Enables AI assistants to analyze local source code, build and query a dependency graph, and suggest skeleton structures for new modules based on existing architectural patterns and conventions.
Enables local, offline inspection and analysis of agentic AI projects by scanning project structure, detecting agent tools, and generating architecture reports through MCP tools, resources, and prompts.
Enables AI clients to safely read, search, understand, and edit local project code and files, with Git inspection, code indexing, and controlled command execution within permissioned workspaces.
Enables AI coding agents to query a repository's architecture through tools for repo maps, token-budgeted context packing, blast-radius analysis, AST file skeletons, and circular dependency detection.