Skip to content
@mindfulcto-labs

mindfulcto labs

Applied AI lab publishing reference implementations of patterns used at exec-engineering altitude. AI governance, agentic harnesses, Graph RAG, LLM control plan

mindfulcto-labs

A small applied-AI lab publishing reference implementations of the patterns I run at exec engineering altitude.

Focus

  • AI governance and Responsible AI — ISO/IEC 42001 Annex A controls, EU AI Act Articles 12–15, NIST AI RMF, UK AI Cyber Code, turned into runtime-enforced policies and evidence-generating logs.
  • Agentic AI harnesses — autonomy budgets, blast-radius controls, regulator-legible audit trails. The shape of the patent I filed at A.P. Moller–Maersk, generalised to non-customs domains.
  • LLM control plane — DLP, PII redaction, prompt-injection defence, ephemeral pods, policy-as-code, observability, evals.
  • Graph RAG and ontology-based retrieval — three-layer semantic ontologies over public regulatory corpora (EUR-Lex AI Act, GDPR, DORA, NIS2).

Principles

  • Every repo is a public reference implementation. No employer IP, no client data, no proprietary architecture. Synthetic and public datasets only.
  • Each repo is paired with a long-form essay on themindfulcto.com explaining the design choices and the trade-offs that produced them.
  • We delete more than we add. The portfolio shrinks before it grows.
  • Plain English. No badge soup. No "revolutionary AI". The code is the claim.

Maintained by

@venkat-uk — Engineering Director leading AI Supported Development, AI Governance, and Responsible AI at a UK retail-data platform. Previously Head of Technology for a logistics platform across 130 countries. Patent application pending on agentic AI for regulated workflows.

License

Unless noted otherwise inside individual repos, code in this organisation is Apache 2.0 and documentation is CC BY-SA 4.0.

Popular repositories Loading

  1. .github .github Public

    Organization profile + meta for mindfulcto-labs

  2. apiloom-ce apiloom-ce Public

    High-performance, open-source API gateway in Go. Routing, auth, rate limiting, unified LLM proxy, sub-millisecond overhead.

    Go

  3. apiloom apiloom Public

    Open-source API intelligence platform. One platform: gateway, portal, AI proxy, governance, management console. Built in Go on Lura + PostgreSQL.

    Go

  4. awesome-ai-governance awesome-ai-governance Public

    Curated, opinionated list of resources for building, governing, and operating AI systems under EU AI Act, ISO/IEC 42001, NIST AI RMF, and UK AI Cyber Code.

  5. agentic-harness agentic-harness Public

    Production-shape agent harness. Autonomy budgets, blast-radius controls, regulator-legible audit trails.

    Python

  6. compliance-as-code compliance-as-code Public

    ISO/IEC 42001 Annex A + EU AI Act Articles 12-15 as code. CLI + library + SPDX 3.0 AIBOM emitter. Plugs into agentic-harness and any LLM gateway.

    Python

Repositories

Showing 9 of 9 repositories

People

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

Top languages

Loading…

Most used topics

Loading…