How EKOS Works

An end-to-end walk from raw files to a cited answer.

One pass through the pipeline

1. ekos build walks the paths in [observe], redacts secrets and PII, and stores content-addressable observation artifacts. It also writes a File object per observed file.
2. ekos recover runs one analyzer per source kind — SQL DDL, Rust/Python/JavaScript/Elixir/Perl ASTs, Git history, GitHub issues, Confluence pages, documents, dbt projects, Pentaho jobs, crate topology — and emits typed KIR (Knowledge Intermediate Representation) objects, relationships and evidence.
3. ekos resolve merges duplicates. Exact-name duplicates from the same source kind merge; fuzzy matches become reviewable unconfirmed SameAs relationships instead of silent merges.
4. ekos compile turns resolved KIR into the Canonical Knowledge Model (CKM), including derived objects such as concentration risks.
5. ekos commit appends the CKM to the ledger, then builds search indexes, subsystem rollups, and (if enabled) LLM descriptions and embeddings.
6. Query. ekos mcp serve exposes the ledger read-only to agents; ekos ask, ekos query and ekos ekl do the same from a terminal.

Details for each stage: Compilation Pipeline.