Skip to main content

Limen Docs

This page is the routing hub for the Limen docs. Use it to choose the right path based on what you are trying to do.

Limen In One Page​

Limen is a Bitcoin alpha research engine for turning market data into experiments, logged analytics, backtests, and decoder cohorts. It keeps the research loop inside one Python system: data preparation, indicators, features, targets, scaling, parameter search, and post-run evaluation.

Limen does not perform downstream trade decisioning or execution. In the wider Vaquum architecture, Origo sits upstream as the data layer, while Nexus, Praxis, and Veritas sit downstream for decisioning, execution, and oversight.

Start Here​

If You Are New To Limen​

  1. Read the product home page
  2. Learn how data enters Limen in Historical Data
  3. Learn how experiments are packaged in Single-File Decoder
  4. Review the shipped patterns in Built-In SFDs
  5. Learn the standard declarative path in Experiment Manifest
  6. Run experiments in Universal Experiment Loop
  7. Review outcomes in Log

If You Want To Author Experiments​

  1. Start with Single-File Decoder
  2. Review the shipped patterns in Built-In SFDs
  3. Continue to Experiment Manifest
  4. Use Indicators, Features, Transforms, Scalers, and Reference Architecture as your reference layer
  5. Run the search in Universal Experiment Loop
  6. If you need adaptive search, continue to Advanced Search and Reducers And Feedback
  7. Inspect results in Log, Benchmark, and Backtest

If You Want To Review Finished Runs​

  1. Start with Log
  2. Compare model behavior in Benchmark
  3. Evaluate trading behavior in Backtest
  4. Review helper metrics in Standard Metrics Library and Reference Architecture
  5. Continue to Trainer and Cohort if you are promoting outputs downstream

If You Want To Extend Limen​

  1. Start with Reference Architecture and Built-In SFDs
  2. Continue to Advanced Search for SearchStrategy, ParamDomain, MSQ, and checkpoints
  3. Continue to Reducers And Feedback for adaptive interventions
  4. Use Utilities when you need the helper layer rather than the main workflow

If You Want To Contribute Or Maintain​

  1. Start with Developer Guidelines
  2. Read the docs contract in Documentation System
  3. Use Contributing Foundational SFDs for SFD work
  4. Use Making Release and Semantic Versioning for maintenance work

How Limen Flows​

  1. Data enters through Historical Data or compatible external OHLC data.
  2. Data can be reshaped with Data Bars when threshold bars are the right research surface.
  3. Indicators, features, transforms, and scalers define the research surface.
  4. An experiment is packaged in an SFD, often starting from Built-In SFDs and usually expressed through an Experiment Manifest.
  5. Universal Experiment Loop executes the search, with Advanced Search and Reducers And Feedback extending the artifact-rich path.
  6. Log, Benchmark, and Backtest explain what happened and why.
  7. Trainer turns selected rounds into reusable sensors.
  8. Cohort defines selector-driven ensemble inference for multi-member decoder aggregation.
  9. Those outputs then move downstream into Nexus and the rest of the Vaquum stack.

Docs Map​

Product Boundary​

Limen Owns​

  • experiment-oriented data access
  • indicator, feature, transform, and scaler composition
  • manifest-driven and custom SFD-based research units
  • parameter sweep and experiment logging
  • benchmark-style analytics and backtesting
  • retraining and cohort construction

Limen Does Not Own​

  • upstream source-of-truth market data infrastructure
  • downstream trade decisioning
  • execution and exchange operations
  • system-wide oversight and audit