LocusQuant

An AI that runs a hedge fund, end to end, and on the record.

A working multi-agent prototype today. Watch it deliberate, backtest, and audit a position, one ticker, on paper. The plan: coordinated swarms that run the whole fund, end to end.

See it run →
5
agent desks live
252d
backtest basis
100%
decisions audited
$0
live capital at risk
How it will work

One continuous loop, from market feed to managed capital.

The target design: every stage running as coordinated agents under a central orchestrator, outputs flowing forward through deterministic gates, and positions feeding back into research. Today the research & selection stage, the Boardroom, is live; the rest is the roadmap.

01
Live Market Feed
02
Thematic Segregation
03
Research & Selection
04
Risk & Direction Gates
05
Execution & Allocation
06
Continuous Stewardship
⟲ feedback loop managed positions and realized outcomes flow back into Research & Selection.
The architecture we're building

Seven coordinated swarms, one meta layer.

The target architecture: specialized agent groups, each owning a stage of the fund's operation. Today one of them runs: the research Boardroom. The rest are the roadmap. Every swarm is a framework of typed capability slots, so governance stays permanent and the agents inside are swappable.

Swarm 01

Ingestion

Agent-supervised data pipelines that file incidents instead of failing silently, feeding search-interest, options-chain and futures-basis data for behavioral and timing signals.

Swarm 02

Prediction

A probability-weighted market model plus a time-series foundation-model ensemble, and a Behavioral Desk scoring attention, prospect-theory and extrapolation signals on the same reality-checked discipline.

Swarm 03

Research

Desks debate into an adjudicated house view, grounded in a shared knowledge graph and policed by deterministic bias gates that catch herding and overconfidence in our own agents.

Swarm 04

Execution

Deliberately not an LLM: a deterministic engine with a timing overlay covering trading windows, calendar-risk days, participation caps and order-to-trade hygiene enforced as policy.

Swarm 05 New

Stewardship

The post-purchase layer: living theses re-underwritten on cadence, deterministic exit discipline through the same gates as entries, a hedging module and a drawdown governor.

Swarm 06

Compliance

OPA rules plus LLM auditors running manipulation-pattern detectors on our own order flow as examiner-ready proof of what we don't do.

Governed autonomy · on the roadmap

Full autonomy, inside an envelope the OS makes impossible to leave.

The governance model we're building (ships v0.8 to v0.9): humans approve a Mandate once, covering its objective, the exact files an agent may touch, its budget, its legal scope. Inside that envelope the agent is fully autonomous; outside it, actions aren't just forbidden, they're impossible, because the mandate compiles to policy in LoQOS.

The Foundry

Governed self-improvement: ratchet loops run experiments on allowlisted surfaces only, each a commit in a per-swarm lineage graph. Everything is reversible; a deterministic scorer, independent of the proposer, decides what's kept.

Shared knowledge graph

One memory across every swarm: entities, claims, forecasts, theses and their provenance. Agents get bounded subgraphs with citations instead of replaying transcripts.

The Bursar

Every token and compute dollar is metered and attributed to an agent, swarm and decision, then reported as net-of-cost P&L, with budget envelopes enforced and safety spend always exempt.

Not AI bolted onto a hedge fund. The fund itself, rebuilt as an operating system.

Trust

The model proposes. Deterministic code disposes.

What makes LocusQuant different from a chatbot pointed at a brokerage: the guardrails are code, not prompts, and every decision is on the record.

Deterministic code gates

Risk boundaries and house-view consistency are enforced by plain Python gates, not prompt guidance a model can talk around. A non-compliant proposal is rejected before it can execute.

Append-only audit trail

Every agent output and gate decision streams to an append-only store, so each decision is traceable back to the inputs that produced it, with no silent overrides.

Honest-by-default UI

Degraded desks, missing data, and gate interventions are surfaced, not hidden. The interface shows what actually happened, including when the system overrode the model.

Status · now

A working prototype, today.

Not a mockup. A running multi-agent system you can watch deliberate, backtest, and audit. Today it runs a single ticker on paper capital, no live money, with every decision recorded.

Operational
Multi-agent deliberation: the Boardroom
Backtesting on a 252-trading-day basis: Strategy Lab
Portfolio & risk views
Full append-only audit log
Built on
LangGraph Groq-served Llama FinBERT SEC EDGAR FRED

Orchestrated multi-agent graphs over Groq-served Llama models, with FinBERT sentiment and grounded market & macro data from SEC EDGAR and FRED.

The system is designed to automate research → prediction → deliberation → execution → stewardship, while humans keep four irreducible seats: exception resolution, compliance judgment, capital allocation, and legal sign-off.

What ships next

From prototype to fund-in-a-box.

The near-term releases from the pipeline, each still paper-traded and routed through the same deterministic gates.

Next releases
v0.5 · in build Replatform: a real web platform with admin console, RBAC, kill switches and hash-chained audit, plus cost-metering taps and slot-based agent loading from day one.
v0.6 Prediction + Behavioral Desk: probabilistic forecasts and behavioral signals, scored against reality; bias gates v1; uncertainty-scaled sizing.
v0.7 Execution + Stewardship: a screened universe worked by a production engine with a timing overlay, plus living theses and deterministic exit discipline.
v0.8 Governance, Mandate & Graph: a mandate console and OPA policy, the knowledge-graph and lineage planes, and the Budget Governor + Bursar.
v0.9 LoQOS + Foundry: an immutable OS runs every agent in its own micro-VM under a policy kernel no agent can route around, with self-improvement ratchet loops on Prediction & Research.
v1.0 Fund-in-a-Box: the Foundry across all swarms, a neural engine trained on the fund's own history, and a first slice of live capital.

View the full pipeline → What's Next

Team

Who's building it.

Divyanshu Bhardwaj
Data Science

Data science background across credit-bureau and fintech systems, forming the quantitative and modeling core of LocusQuant.

Ayush Vaishnav
Enterprise Integration

Enterprise integration background, wiring the operating system into robust, production-grade infrastructure.

Reach a founder directly through the .

Get access

See the fund run, on the record.

Request access to the live prototype and watch the agents research, deliberate, backtest, and audit a position, one ticker, on paper, every decision recorded.

Explore LoQOS

Investors & partners welcome · no live capital at risk today