Systems & Research

Attention is finite. These are the systems that are moving. Implementation stays private — what's here is the architecture and what I learned building it.

Now

7

The work that is actually going somewhere. Start here.

Decatron

The agent harness — what actually drives the fleet

A harness that makes agent work auditable: one model does the task, a model from a different vendor reviews it, and every byte and verdict goes in an append-only record. "The model checked its own work" is not evidence.

diagram 2 posts

Aurelia

The local assistant — Tessera is the kernel

The local assistant. A prompt is a comment, not a boundary: unattended actors cannot touch the world, and replies are checked against the record before I see them. Tessera is the kernel — two trees, presence and absence — not the whole system.

diagram 12 posts

Lumen

Transport, not translator

A dispatch harness: one prompt in, the model's answer back, not a byte altered. 1.0.0 is shipped. Most agent CLIs decorate what passes through them; once they edit the bytes you can no longer tell what the model did.

diagram 1 post

Isosceles

Evolutionary search — agents propose, acceptance is mechanical

Coding agents propose program variants; a deterministic evaluator scores them; mechanical gates accept or reject. The point was never the optimized programs — it was how much of the loop can verify itself. Not the Discord collaborator, which shares the name.

diagram 1 post

Cosmos

A physics engine for knowledge — measured, not assumed

A holographic state engine: a knowledge graph treated as a gravitational system, with a real fluid solver, tensor-network geometry, and a free-energy field an active-inference agent works to reduce. Every gauge measured or explicitly gated; self-improvement gated on self-measurement.

diagram 2 posts

Diametric

Two adversarial AI entities, co-evolving

A game where two AI entities co-evolve through repeated encounters. Deterministic Rust owns every real-time encounter; the LLM is confined to between-encounter strategy. The long bet of the bunch.

diagram 3 posts

Tesseract

Diffusion reasoning — not the same system as Tessera

A thin deterministic layer — planning, memory, sequencing, verification — around an open-weights diffusion model. The bet is that orchestration, not the model, is where usable reasoning gets built. Not Tessera.

diagram 1 post

Earlier

9

Real work, not the current path. Pages stay so old links and posts still resolve.

Silent Forest

Autonomous infrastructure monitoring

A monitoring system that watches infrastructure from the outside and reports in plain language. The core has operated unattended for 60+ days at a stretch, on hardware I own, with no cloud AI dependency.

diagram 1 post

TOMA

Tool Orchestration Meta-Agent — governed tool use for the ecosystem

Shared infrastructure that governs how every agent in the ecosystem calls tools. Deterministic validation, dispatch, and signed evidence ledger — the LLM never runs in the invocation hot path.

diagram 2 posts

Phenotype

Expressing the genome substrate into a running agent

The agent runtime that composes validated genes into a working agent. Consumes the Genome substrate at a versioned boundary; enforces the proven boundary structurally, by construction.

diagram 1 post

Genome

Research: can agent identity be encoded as inspectable substrate?

A completed research arc. Found a precisely-bounded structural substrate — and the boundary itself is the result. The negative finding (no emergent synergy) came with a mechanism, and that mechanism is the foundational commitment.

diagram

Scarlett

Embodied agent with deterministic interiority

An embodied agent with a continuous inner life. Two-clock architecture: deterministic fast clock for real-time presence, slower reasoning clock for deliberation. Affect lives in the deterministic core, not the model.

1 post

Planets

Knowledge infrastructure — structured claims that survive the agent

A knowledge architecture where the accumulated state — the Planet — is primary and agents are ephemeral. Agents emit deltas; an integration layer evaluates and persists them as claims with provenance. The knowledge outlasts any agent that produced it.

diagram 1 post

Workspace agent

Discord collaborator — earlier Isosceles, not the search harness

A Discord collaborator agent with a two-clock boundary and real tool agency. Published here as Isosceles; that name now belongs to the evolutionary-search harness. This page stays so the existing posts and URL still resolve. It is earlier work, not the systems that are moving.

diagram 3 posts

The Decagon Platform

The coherence spine — keeping a multi-agent ecosystem honest about itself

The part of the ecosystem that keeps the system's model of itself accurate — what each component is, what it's for, whether it's maintained, whether it's alive. Accuracy is not a virtue you sustain by vigilance; it is a property you generate from ground truth and enforce with a gate.

diagram 2 posts

Loom

Literature-based discovery, measured against elapsed time

A literature-mining engine tested on whether it could surface drug–disease joins validated only after its corpus ended. It failed twice, under bars frozen in advance — and the located failure, with a control that demonstrably could score, is the result.

diagram 3 posts