Skip to content
ENTERPRISE

Built to behanded to an auditor.

DjiniousEngineering is API-first and self-hostable. Every capability is a REST endpoint, the whole System Ledger is exposed over one MCP endpoint, and every item on the digital thread carries a revision, a validation state and the evidence it was closed against.

The DjiniousEngineering agent runtime: streamed reasoning, ledger tool calls over MCP, and the human approval queue for actions the autonomy policy holds back.The DjiniousEngineering agent runtime: streamed reasoning, ledger tool calls over MCP, and the human approval queue for actions the autonomy policy holds back.
One MCP endpoint, about thirty tools — an external agent works the ledger with the same guarantees a human gets.Agent runtime · MCP + REST
INTEGRATE

Fits the toolchain you already drive

  • Every capability is an endpoint

    The whole platform is API-first: the same REST API the product's own front end uses is the one you build against. Nothing the UI can do is off-limits to a script or a service on your side.

  • One MCP endpoint for the ledger

    The System Ledger is exposed over a single MCP endpoint of about thirty tools — read the thread, take the next step, check a gate, append or supersede an item — so an external agent can navigate the whole ledger with the same guarantees a human gets.

  • Scoped tokens and a CLI

    JWT with OIDC secures the UI; scoped, long-lived API tokens secure automation, and MCP takes an X-API-Key. The `dje` CLI drives the agent straight from a terminal, so a run belongs in a pipeline as easily as in the browser.

  • One sealed hub to six apps

    Connectors reach DjiniousLab, Workshop, Safe, World, Map and CC from one authenticated place, credentials sealed at rest with AES-256-GCM. Numerical models, component integration, verified code and geospatial data arrive on the ledger with their provenance intact.

GOVERN

Answers who validated what, and against what evidence

  • A human clears every gate

    The agent works the ledger stage by stage and stops at each review gate — SRR, PDR, CDR, TRR, PRR — until the upstream items are user-validated against explicit criteria. It proposes; a person validates. No gate passes itself.

  • State and revision on every item

    Each item moves draft → proposed → agent_validated → user_validated, carries a revision, and names its artifact type. `agent_validated` means awaiting a human; `user_validated` is the human's signature on the record.

  • Supersede with a reason, staleness follows

    Replacing an item requires a written reason, and changing its content marks everything reachable forward along the produces edges stale — a stale item stops counting as a valid contract fulfilment, so nothing silently rests on a moved foundation.

  • Evidence you can defend

    Eight evidence classes rank MEASURED down to UNKNOWN, and a requirement cannot close on evidence weaker than its verification method demands — UNKNOWN blocks closure outright. Roles are admin, user and viewer, with a per-user autonomy policy over what the agent may do unattended.

OPERATE

Standards-native, and it runs where you need it

  • The lifecycle is the standard

    The eleven stages are named after ISO/IEC/IEEE 15288 processes, requirements follow ISO/IEC/IEEE 29148 and architecture follows ISO/IEC/IEEE 42010. The Technical Data Package is the release artifact, not an afterthought bolted on at the end.

  • Self-hosted by default

    A Docker Swarm stack — the Bun application on React 19, backed by SurrealDB for graph, vectors and full-text in one store — behind your reverse proxy. Your data and your thread stay on your infrastructure.

  • Secrets sealed, auth explicit

    Authentication is JWT over OIDC; connector credentials and other secrets are sealed at rest with AES-256-GCM. Access is scoped by role, and automation is scoped by token — nothing shares a blanket key.

  • One model over the whole system

    ELANG is one declarative, machine-checkable model of the system — twenty-seven entity kinds across four pillars, checked against twenty-six well-formedness rules and reported at a conformance level from L0 to L3 with its gap list. The thread stays legible to a reviewer and to a machine at once.

BASELINE

Release a data package, not a folder nobody trusts

The Technical Data Package is assembled from the traced thread — every deliverable tied back to the ledger items, revisions and evidence it was built on, not transcribed off them by hand.

The DjiniousEngineering deliverables view exporting the Technical Data Package, each document tied to its ledger items, revisions and validation state.The DjiniousEngineering deliverables view exporting the Technical Data Package, each document tied to its ledger items, revisions and validation state.
The Technical Data Package: the release artifact, assembled from the traced thread rather than transcribed off it.

Send us your hardest requirement.

An air-gapped deployment, a standard we have not named, a review gate with criteria of your own, an evidence bar nothing in the field can meet yet. We would rather tell you what is not built than find out together in month three.