Six releases from pipeline to fund-in-a-box.

What's shipping after v1.0.0-PREVIEW: a prediction swarm scored against reality, a production execution engine, a governance layer, and an operating system where the guardrails live below every agent.

The AI proposes. The code disposes.

$ cd ~ — back to the main page

The pipeline.

Each version ships a usable fund. Value first, armor when there's something worth armoring, learning loop once there's history to learn from.

v0.5 — in build

Replatform

Streamlit retires. A real web platform: browser-based Admin Console with role-based access, kill switches, and live Boardroom streaming — on an event-driven core with a tamper-evident, hash-chained audit store.

admin console rbac kill switches hash-chained audit
v0.6

Prediction Swarm

A dedicated forecasting swarm: regime detection, time-series foundation models, and Bayesian estimators issue probabilistic predictions into a registry — then get scored against realized data. Calibration decides whose forecasts the fund trusts, and position size shrinks automatically as uncertainty rises.

forecast registry reality scoring regime engine uncertainty-scaled sizing
v0.7

Execution & Breadth

From one ticker to a screened universe. An ingestion swarm supervises every data feed, an uncertainty-driven screener decides which names earn a full boardroom, and a production-grade execution engine works orders — paper first, always through the gates.

execution engine universe screener ingestion swarm live orchestration map
v0.8

Governance Layer

A compliance swarm audits every agent against the rulebook and files findings with citations. Humans steer any agent through an instruction console — and a dedicated risk agent scores every instruction against fund strategy before it dispatches. An analytics agent can surface any dataset any agent ever used.

compliance swarm instruction console instruction risk scoring analytics agent
v0.9

LocusOS

The fund becomes a machine. An immutable, reproducible operating-system image runs every agent in its own micro-VM with kernel-level network and policy enforcement. Validated "golden rules" compile into an OS-level policy kernel that no agent — however clever, however compromised — can route around.

immutable os image per-agent micro-vms os-level policy kernel gpu-ready runtime
v1.0

Fund-in-a-Box

The learning loop closes: a neural engine trains on the fund's own audit history to tune strategy weights, and a meta-research agent runs sandboxed experiments on the agents themselves. Multi-book support. Install the image, get a hedge fund.

neural engine meta-research agent golden-rule lifecycle multi-book

Three swarms become six.

Specialists, not a monolith. Every swarm evolves — and every swarm is watched.

// swarm 01

Ingestion

Agent-supervised data pipelines that detect drift, gaps, and staleness — filing incidents instead of failing silently.

// swarm 02

Prediction

Probabilistic forecasts with credible intervals, scored daily against realized data. Skill earns trust; decay loses it.

// swarm 03

Research

Desks, debates, and adjudicated house views — consuming predictions weighted by the predictor's live track record.

// swarm 04

Execution

Deliberately not an LLM: a deterministic engine that only accepts tickets that clear every gate and every policy.

// swarm 05

Compliance

Continuous rule checks on every action, plus auditors that replay agent histories against regulation — with citations.

// meta

Neural Engine & Meta-Research

The audit trail becomes training data. A research agent studies the agents themselves and A/B tests improvements in sandboxes.

Where humans stay.

We automate everything a fund does that machines do better — and we're explicit about what they don't.

function who runs it
Research, forecasting, backtesting, order flow, monitoring AUTOMATED — gate-checked
Reconciliation & NAV AUTOMATED
Exception resolution HUMAN
Compliance judgment & regulatory sign-off HUMAN
Capital allocation across strategies HUMAN — machine proposes
Crisis discretion & kill switches HUMAN — by design

Follow the build.

Paper-trading preview today; each release above lands with a recorded, auditable run.