Transform Directories into Knowledge Graphs with Astria AI

Transform Directories into Knowledge Graphs with Astria AI

Astria AI skill effortlessly transforms any directory of source code into a queryable knowledge graph. It employs AST-based extraction via tree-sitter to conduct fast and reliable analysis, rendering complex directories into structured data insights.

What this skill does

• Automatically determines the state of the knowledge graph when executed and builds or updates it as necessary.
• If no graph exists, it constructs a new one using the full directory data.
• For existing graphs, it assesses if an update is required based on file changes, and performs updates incrementally.
• After processing, it verifies the existence of nodes ensuring supported files are included.
• Generates a plain-language graph report summarising the graph structure and key findings.

Who it is for

• Software developers seeking to convert source code directories into searchable data structures.
• AI researchers and engineers desiring structured intelligence on codebases for analysis and evaluation.
• Development teams leveraging AI coding agents like Claude Code, Cursor, and Codex to optimise their coding environment.

Use cases

• Teams needing to assess and visualise the relationship between various components in large codebases.
• Developers tasked with maintaining legacy systems and requiring insights into the framework architecture through a structured report.
• AI professionals exploring community detection, hub node analysis, and other advanced graph analytics for code repositories.

Technical details

• Utilises abstract-syntax-tree (AST) methodology via tree-sitter for efficient syntax analysis.
• Compatible with numerous programming languages, such as Python, JavaScript, Rust, Go, and Java, among others.
• Facilitates integration with AI agent platforms, enhancing capabilities for intelligent code processing.
• Ensures that graph data remain current with state verification and incremental updates.

Source & Licence

This package is built on open-source work published by Nodesify (Nodesify/astria) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.