Foundations

R / 04

Ordivon Computing

Keep cognition, Task continuity, semantic execution, and machine execution separable—and delete abstractions that mature systems already carry.

The research and conformance root for persistent work performed with probabilistic models. Computing defines the contracts that other projects test rather than becoming another production runtime.

Maturity
Active research foundation
Built for
Agent-system designers deciding which boundaries deserve to become shared infrastructure.
Latest proof
Strong workflow, retrieval, idempotency, and provider baselines reduced the proposed core instead of validating a larger platform.

Question this project must answer

Which facts and contracts must remain stable when models, Hosts, tools, and execution backends change?

Working model

Model RuntimeAgent HostTask RuntimeSemantic KernelExecution RuntimeOperating System

Where it stands now

Active research foundation

The model-to-work stack and Harness H1–H5 are closed as canonical research. Computing now distinguishes mature Provider Harnesses from the ready Ordivon Harness v0 construction question for bare model APIs.

Capability evidence

H1–H5boundary stages closed
493,294H5 reported tokens
1ready Harness construction question

What this project owns

Facts it must preserve and may commit.

  • Stack model
  • Semantic contracts
  • Reference experiments
  • Conformance

What it leaves elsewhere

Responsibilities another owner or mature system should retain.

  • No production Tasks
  • No physical Jobs
  • No place in the execution path

Questions that can still change the project

01

testing

Which contracts survive a second independent workload without being tailored to one repository?

02

testing

When should an Agent act, wait, observe, refuse, reconcile, or request a decision?

03

open

Which Task Runtime objects are required by asynchronous waiting and Join semantics?

04

answered

Which Agent-native responsibilities remain after strong classical baselines?