Skip to content
@SantanderAI

Santander AI Open Source

Open source AI projects from Banco Santander AI Lab. Responsible AI, MLOps, graph ML and LLM evaluation for financial services. Apache-2.0. PRs welcome.

SantanderAI

Open source artificial intelligence projects from Banco Santander AI Lab

Website License Code of Conduct Contact


Our mission

We build and open source AI tools that advance small models, harness engineering, evolving agents, responsible AI, MLOps and graph machine learning for the financial services industry. By contributing back to the open source ecosystem we help raise the bar for trustworthy AI in banking — and we give back to the community whose work powers our own innovation.

Featured projects

Project Description License Status
ralph A configurable Bash/PowerShell loop that runs an AI coding CLI with a fresh session each iteration. Apache-2.0 ✅ Active
ralph-vault-skill Skill to generate the knowledge vault for projects using the Ralph loop. Apache-2.0 ✅ Active
auto-bayesian Config-driven, interpretable Bayesian network training for relational tabular data. Apache-2.0 ✅ Active
autoguardrails Alignment-research scaffold (autoresearch-style) for LLM guardrails over a single policy.md surface. Apache-2.0 ✅ Active
causal-perception-implementation ML research code for causal perception — comparing competing structural causal models via interventional and counterfactual distributions, applied to fair credit decisions. Apache-2.0 ✅ Active
gen-fraud-graph Synthetic fraud graph generator for training and benchmarking graph-based fraud detection models. Scales to 100M+ accounts. Apache-2.0 ✅ Active
genetic-algorithm A dependency-free Python genetic-algorithm engine with pluggable fitness criteria — a reusable search core for an LLM/AI autoresearcher. Apache-2.0 ✅ Active
linear-adapter-trainer Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG). Apache-2.0 ✅ Active
llm_bridge A tiny, vendor-neutral LLM client library — one interface with pluggable adapters for OpenAI, AWS Bedrock and Google Gemini, or bring your own backend. Apache-2.0 ✅ Active
mech-gov-framework Mechanical Governance for LLM Decisions — model-agnostic governance regimes, hard gates and governance metrics for high-stakes LLM decision systems. Apache-2.0 ✅ Active
mutatis-mutandis Situation testing for discrimination analysis with counterfactual comparators — research code for the paper 'Mutatis Mutandis: Revisiting the Comparator in Discrimination Testing'. Apache-2.0 ✅ Active
sota-stressed-datasets Open benchmark datasets republished in stressed form to evaluate ML/LLM robustness. Curated by Santander AI Lab. CC BY 4.0 + Apache-2.0 ✅ Active

All projects use synthetic or anonymised data only. No real customer information is published.

Open source governance

Our Open Source Programme Office (OSPO) runs a transparent two-track review for every project considered for public release:

  • Fast Track — forks, generic tools, tutorials, datasets, SDKs without business logic. Reviewed by OSPO Lead with automated scans (SLA < 4 hours).
  • Full Track — AI models, frameworks with IP, code that touched internal data. Reviewed by a FOSS Review Board (OSPO Lead + Legal + CISO + Architect). SLA 2-4 weeks.

Full policy: GOVERNANCE.md

Contributing

We welcome contributions from everyone. Please read:

  • CONTRIBUTING.md — how to submit issues and pull requests
  • CODE_OF_CONDUCT.md — Contributor Covenant v2.1
  • SECURITY.md — responsible disclosure
  • All contributors agree to our Contributor License Agreement (CLA) on first PR

Contact


Built with ❤️ by AI Labs · Banco Santander · Madrid 🇪🇸

Open code · Responsible AI · For the community

Pinned Loading

  1. gen-fraud-graph gen-fraud-graph Public

    Synthetic fraud graph generator for benchmarking graph-based fraud detection models in financial services.

    Python 94 18

Repositories

Showing 10 of 14 repositories
  • causal-perception-implementation Public

    Machine learning research code for causal perception: comparing competing structural causal models (SCMs) via interventional and counterfactual distributions, applied to fair credit decisions. Open source by Santander AI Lab.

    SantanderAI/causal-perception-implementation’s past year of commit activity
    Python 15 Apache-2.0 2 0 1 Updated Jun 22, 2026
  • ralph-vault-skill Public

    Skill to generate the knowledge vault for projects using the Ralph loop

    SantanderAI/ralph-vault-skill’s past year of commit activity
    Python 31 Apache-2.0 5 1 0 Updated Jun 22, 2026
  • gen-fraud-graph Public

    Synthetic fraud graph generator for benchmarking graph-based fraud detection models in financial services.

    SantanderAI/gen-fraud-graph’s past year of commit activity
    Python 94 Apache-2.0 18 0 1 Updated Jun 21, 2026
  • .github Public
    SantanderAI/.github’s past year of commit activity
    3 2 0 1 Updated Jun 21, 2026
  • sota-stressed-datasets Public

    Open benchmark datasets republished in stressed form to evaluate ML/LLM robustness. Curated by Santander AI Lab.

    SantanderAI/sota-stressed-datasets’s past year of commit activity
    HTML 20 2 1 0 Updated Jun 21, 2026
  • mutatis-mutandis Public

    Situation testing for discrimination analysis with counterfactual comparators — research code for the paper 'Mutatis Mutandis: Revisiting the Comparator in Discrimination Testing'

    SantanderAI/mutatis-mutandis’s past year of commit activity
    Jupyter Notebook 11 Apache-2.0 0 0 0 Updated Jun 21, 2026
  • mech-gov-framework Public

    Mechanical Governance for LLM Decisions — model-agnostic governance regimes (R1/R2/R3), hard gates, entropy commit-reveal and governance metrics for high-stakes LLM decision systems.

    SantanderAI/mech-gov-framework’s past year of commit activity
    Python 31 Apache-2.0 7 0 0 Updated Jun 21, 2026
  • llm_bridge Public

    A tiny, vendor-neutral LLM client library — one interface (LLMClient) with pluggable adapters for OpenAI, AWS Bedrock and Google Gemini, or bring your own backend.

    SantanderAI/llm_bridge’s past year of commit activity
    Python 25 Apache-2.0 7 1 0 Updated Jun 21, 2026
  • linear-adapter-trainer Public

    Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

    SantanderAI/linear-adapter-trainer’s past year of commit activity
    Python 12 Apache-2.0 4 1 0 Updated Jun 21, 2026
  • genetic-algorithm Public

    A dependency-free Python genetic-algorithm engine with pluggable fitness criteria — the reusable search core for an LLM/AI autoresearcher.

    SantanderAI/genetic-algorithm’s past year of commit activity
    Python 16 Apache-2.0 5 0 0 Updated Jun 21, 2026

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics

Loading…