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.
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. Reading everything costs the whole context window. The graph answers in ~3,000 tokens — measured at 50–110× fewer tokens per query on real repos (printed honestly after every run; varies by corpus — see Benchmarks and evidence).
Three things a folder full of files can't give you
- 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.
- An honest audit trail — every edge is labeled
EXTRACTED/INFERRED/AMBIGUOUSwith a numeric confidence score. You always know what was found in the source versus deduced, and--detail highfilters to only declared facts. - 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 nine 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 and the head-to-head vs the original Graphify
- 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.