The DKE Python language

The language your LLM reasons in — and can prove.

DKE Python is the open, published language for DKE, the Deterministic Knowledge Engine. You write a program; DKE compiles it and runs it against your data, and every answer comes back grounded — carrying its provenance. The specification is MIT, so you can build your own tooling against it: compilers, linters, formatters, highlighters.

MIT spec .dpy Provenance-tracked Deterministic

DKE MCP — attach the engine to your agent

DKE runs as a service your LLM or agent connects to over MCP. Point a client at dke.langsyn.net, hand it your access key, and your assistant can write and run DKE Python, store and recall what it learns, and get answers it can trace — all through the same tool interface it already speaks.

Speaks MCP

DKE is served as a small set of standard tools — compile, run, recall, explain. Any MCP-capable client can drive it, no bespoke SDK required.

Your key, your store

Each account gets an access key and an isolated store. What your agent teaches DKE stays yours — nothing is shared across accounts.

Answers you can trace

Every result your agent gets back comes grounded in the facts it rested on — a derivation you can follow, not a guess you have to trust.

Get an access key Read the spec

DKE Studio — run DKE Python in your browser

DKE Studio is the fastest way to watch the engine work. Write a DKE Python program, run it live, and see the answer come back grounded — free, no signup, nothing stored.

Every run gets a fresh, disposable workspace. Load an example or start from a blank program, press run, and read the result with its provenance attached. When it changes how your work flows, get an access key and keep the engine attached from your own client.

Open DKE Studio

DKE docs — the published language

Everything you need to program DKE, published and versioned: the normative specification, the language reference, and a hands-on tutorial. The spec is MIT — read it, build against it, hold us to it.