Introduction

astria turns any folder into a queryable knowledge graph — deterministic AST extraction in Rust, optional local-embedding semantics, zero API keys, everything on your machine.

astria is inspired by the Python Graphify project's core idea — turn a corpus into a queryable knowledge graph — but it is an independent, from-scratch implementation: a deterministic, offline-first Rust/tree-sitter pipeline, not a fork or a port. astria is not affiliated with, sponsored by, or endorsed by the Graphify project or Graphify Labs.

You drop into an unfamiliar repo and need to know: what is load-bearing here, what breaks if I change this, where does auth live, how do these two modules connect. Astria returns a budgeted graph view with source locations and explicit provenance. Historical corpus-to-query token ratios describe output size, while the paired retrieval validation measures file recall, symbol retrieval, response budgets, and latency against pinned corpora.

Three things a folder full of files can't give you

1. Structure that survives the session — hub files, god nodes, communities, and the blast radius of any change, stored in SQLite and refreshed incrementally as code changes.
2. An honest audit trail — every edge is labeled EXTRACTED / INFERRED / AMBIGUOUS with a numeric confidence score. You always know what was found in the source versus deduced, and --detail high filters to only declared facts.
3. Answers for agents and humans — query it from the CLI, from any AI agent via MCP, or just read the exported markdown wiki with plain file links.

Where to go next

• Getting started — install and run your first graph
• Agent integration — wire the graph into Claude Code, Codex, Cursor, …
• CLI reference — every command and flag
• MCP tools reference — the ten tools your agent can call
• Wiki and exports — markdown wiki, Obsidian vault, HTML viewer, Neo4j
• Semantic enrichment — local embeddings and LLM backends
• Global graph — one queryable store across repos
• Memory and learning — learned edges and curated Q/A memory
• Troubleshooting — when something looks wrong
• Benchmarks and evidence — measured numbers, the head-to-head vs the original Graphify, and the retrieval-quality harnesses (recall@k, blind judging, LoCoMo)
• Architecture — how the pipeline works under the hood

Worked examples with honest reviews — the tool run on itself, including what the graph got wrong — live in the worked/ directory of the repository, alongside a head-to-head comparison against the Python Graphify project that inspired it, run on the same corpus.