Bitcoin research and trading platform for systematic operators.

Five open-source modules close the loop from market data to auditable execution. The strategy you deploy is the strategy you tested.

Get started on GitHub

Limen · research loop

# From data to backtest in 2 minutes

import limen
from limen.data import HistoricalData

historical = HistoricalData()
historical.get_spot_klines(kline_size=7200)
uel = limen.UniversalExperimentLoop(
    data=historical.data,
    sfd=limen.sfd.logreg_binary,
)
uel.run(
    experiment_name="logreg-first",
    prep_each_round=True,
)

Five modules. One closed loop.

Each module works alone, all five run together as a closed loop, and every module connects to an existing stack.

Origo

The data layer

Event-sourced market data platform for deterministic, replayable financial data access.
Limen

The research engine

Turns Bitcoin market data into searchable alpha, backtested signals, and decoder cohorts.
Nexus

The decision layer

Turns alpha signals into validated trading decisions, controlled capital deployment, and recoverable manager state.
Praxis

The execution system

Turns trading decisions into execution, durable state, and auditable outcomes.
Veritas

The source of truth

Turns the research-to-trade lifecycle into an auditable and replayable proof bundle. First release Q3/26.

The strategy you test is the strategy you deploy.

Each step is an excerpt from the module's interface as it stands; names carry over from the step before, and each repository documents the full path.

Origo

Connect the data

Kline rollups

from origo.query import binance_spot_kline_rollups

klines = binance_spot_kline_rollups.time_month(
    interval_minutes=15,
    year=2026,
    month=6,
)

Limen

Research and backtest

Experiment loop

import limen

uel = limen.UniversalExperimentLoop(
    data=klines,
    sfd=limen.sfd.logreg_binary,
)
uel.run(
    experiment_name="logreg-first",
    prep_each_round=True,
)

Nexus

Set the boundaries

Instance config

from decimal import Decimal
from nexus import InstanceConfig

config = InstanceConfig(
    account_id="main",
    venue="binance_spot",
    capital_pct={"logreg-first": Decimal("10")},
)

Praxis

Execute and reconcile

Trading runtime

from praxis import Trading, TradingConfig

trading = Trading(
    config=TradingConfig(epoch_id=1),
    event_spine=spine,  # the event log
)
await trading.start()

Don't trust. Verify.

Closed-source trading software is a structural contradiction for a financial system built to eliminate counterparty risk. A black box demands what Bitcoin was designed to remove: trust in an intermediary.

github.com/vaquum

Fig. 01. Seed 7 always draws these same rings.

Parametric · seed 7

Every configuration testable. Every state traceable.

Read the documentation, audit the code, run the research, and judge the results.

Get started on GitHub