The product map

What we build — and how far along each part is.

One thesis across three planes: a mind that persists, a ground that can’t lie, and rules that hold outside the model. Every part carries an honest status — shipped, in closed alpha, in active development, demonstrated, or researched.

Long-horizon agents

Mind

Persistent cognition

Beliefs, memory, trust, and decision state for agents that develop over time.

Taniwha Engine

Active development

Current generation in active development; a first-generation research line still powers Briarwatch.

  • Per-agent belief graphs with provenance
  • Memory, consolidation, and forgetting
  • Trust that builds slowly and collapses fast

Kōrero

Active development

A workspace-resident agent that turns team conversation into durable, anchored records. In build — not yet running against a live workspace.

  • Lives in Slack, capturing conversation as it happens
  • Distills settled threads into records — roadmap, decisions, direction
  • Proposes replies in a colleague's voice, under restraint

Ground

Checkable world-state

Deterministic worlds an agent can observe, question, and be wrong about — grown from a seed, or derived from a repository's own history.

Kano

Active development

Reproducible per engine version — no unseeded randomness, no mutable world database.

  • Whole worlds grown from a single seed
  • Causal — each layer conditioned on the one beneath
  • Queryable by AI over a tool protocol

Pono

Active development

In daily internal use grounding our own agent sessions; reaches teams through Kete. Pre-registered readouts published — misses included.

  • A world derived from a repository's own history
  • Deterministic — no AI anywhere in the derivation
  • Answers what changed, what's current, and why — with citations

Demonstrations

Public proof, labelled by engine generation

Briarwatch

Research

First-generation research line

Long-run social-cognition simulation and the validation environment for the first-generation engine.

Copperhollow

Demonstration

Current generation

Current-generation minds on deterministic ground — a mining camp with a reason to exist.

Kano Showcase

Public alpha

Current generation

Walk a pre-generated world in Hīkoi, a first-person viewer, then ask it why — point at a ridge and the world explains the forces that raised it. Deterministic, offline, and queryable by your own AI over MCP. Alpha binaries and the baked world are downloadable from GitHub.

Assurance

Rules outside the model

Enforce policy on agent actions and keep an audit trail — independent of any one model.

Ārai

Shipped

Open source (Apache-2.0 / MIT), runs locally, no hosted service required.

  • Pre-flight gate on agent tool calls
  • Enforced, advisory, or observed per integration
  • Hash-chained local audit log

built on ↑

Kete

Closed alpha

The organisation platform built around the Ārai core.

  • Org policy across agents, classed per tool
  • Audit retention, query, and export
  • Structural map of a codebase

Research

Result within scope; value still under test

Grounding readouts

Research

Pre-registered twin-session experiments — grounded vs ungrounded on the same commit — that hold the ground layer to account in public. Three pairs published, including our own instrument's miss.

About this view

A curated overview

This is a public-facing view of our development surface — what we’re building and roughly how far along each part is. It’s a snapshot we curate and refresh as things mature, rather than a live feed.

It’s meant to show the shape of the work at a glance, not the granular state of any individual component. For the detail behind a given part, follow it through to its own page.