EKOS
Compile enterprise knowledge once, ask LLMs cheaply
Start new thread

EKOS - Evidence-backed knowledge, compiled from your stack

by•
EKOS compiles heterogeneous enterprise sources — code, SQL schemas, ETL pipelines, git history, CI/CD, GitHub issues, Confluence, docs — into a single append-only, evidence-backed ledger. Every fact traces back to where it came from. Conflicts between sources are surfaced with citations, not silently resolved. When EKOS doesn't know something, it says "unknown" instead of guessing. Open source, Rust-based — built for teams tired of AI tools that answer confidently and wrongly.

Add a comment

Replies

Best
Maker
📌
👋 Hi Product Hunt! I'm Alexey, the creator of EKOS. I built EKOS after realizing that AI coding assistants still struggle to understand large codebases. Instead of relying only on embeddings and raw source files, EKOS compiles repositories into structured knowledge that can be exposed through an MCP server. Today EKOS can: • Generate an MCP server from a GitHub repository • Generate technical documentation from source code • Produce architecture-aware knowledge for AI assistants This is an early open-source project, and I'm actively building it in public. I'd love your feedback: • What would you use it for? • Which integrations should I build next? • What is missing? Thanks for checking it out! 🚀
Maker

Maker update — distributed storage + a real query engine landed this week 🚀

Two big pieces shipped since launch, both proven against real workloads, not just unit tests:

1. Distributed storage & query is feature-complete (v1). EKOS can now split a knowledge base across partitions and serve reads/writes from independent worker nodes backed by S3/Azure/local object storage — a coordinator hands out write leases, query workers cache and serve partitions, and cross-shard search does a real BM25 top-k merge instead of a naive concat.

We didn't just call it done and move on — we ran two full autonomous end-to-end tests against real 90+ partition workloads (MinIO, live LLM provider, the works). They found 8 real defects unit tests never caught: a runtime panic on the object-store path, a query worker that took down the whole cluster when killed, a heartbeat interval that silently expired write leases mid-pipeline. All 8 are fixed with regression tests, and the reports are public in the repo. If a demo only shows the happy path, it's marketing, not evidence — so we publish the failures too.

2. A real compiled-knowledge query engine, not just "dump some JSON at the LLM." Natural-language questions now compile into a typed query plan, execute against structured facts + graph + search, and hand the model a flat set of atomic, source-cited claims — file, line, extractor, confidence — instead of whole objects for it to re-derive structure from. This is the same "compile once, trust the artifact" philosophy applied to retrieval itself.

Both are on main today. As always — open source, evidence-backed, gaps documented rather than hidden. Happy to answer questions about either piece below 👇

Maker

Hey Product Hunt 👋 Maker here with an update on EKOS.

Quick recap: EKOS is an open-source (MIT) knowledge compiler written in Rust. It turns your scattered engineering estate (repos, docs, Confluence, legacy ETL) into a queryable knowledge graph that Claude Code and other agents can use through MCP.

What shipped recently:

🔁 Legacy transformation recovery: `ekos recover` compiles Pentaho/Kettle jobs (.ktr/.kjb), SQL views and stored procedures into one shared Transformation IR. You can now diff old ETL logic against a newly drafted pipeline and see exactly which business rules changed.

🧩 Identity resolution: `ekos identity scan` finds the same table, column or entity under different names across systems, with a review tool so a human confirms the matches.

🛠 New MCP tools for Claude Code: transformation_explain / transformation_diff, impact analysis, dependents, neighborhood search and more. Read-only by default, so it's safe to point an agent at it.

Take a look at:

site

Demo Videos: