01 / Cloud & MLOps
OpenMed MLOps
An educational MLOps demonstration that trains a classifier on synthetic patient data with Kubeflow Pipelines and records experiments in MLflow on Kubernetes.
PythonKubernetesKubeflowMLflow
Projects, from idea
to infrastructure.
Applied machine learning, reproducible tooling, and cloud infrastructure. A collection of projects and engineering practices across models, pipelines, and the systems that support them.
Explore my current research interestsSystems, tools, and applied learning.
Source-linked projects across cloud infrastructure, AI tooling, education, and applied machine learning.
02 / Cloud & MLOps
Local Platform Infrastructure
Terraform-managed local Docker environments with isolated application and PostgreSQL networks, MinIO remote state, and reviewed infrastructure delivery workflows.
TerraformDockerPostgreSQLMinIO
03 / Apps & Tools
Recall MCP
Persistent, searchable memory for MCP-capable AI agents, with SQLite full-text search and tools for saving, retrieving, and managing memories across sessions.
TypeScriptNode.jsMCPSQLite
04 / Apps & Tools
PAL Tech Learning Hub
An offline-first technology learning application with interactive labs, quizzes, coding games, local learner profiles, and facilitator tools.
TypeScriptReactPWAVite
05 / AI & Data
LocalTongue Audio Classifier
A Flask application that classifies uploaded audio as Akan, Dagbani, or Ikposo using mel-spectrogram features and a TensorFlow/Keras model.
PythonFlaskTensorFlowlibrosa
06 / Apps & Tools
Loop Engineering Studio
A browser-based planning tool for repeatable AI agent loops, including verification gates, human review, retry policies, and JSON, YAML, or Markdown export.
JavaScriptAgent toolingWorkflow design
07 / Apps & Tools
Health Sentinel
A personal wellness prototype that reads Android Health Connect summaries, stores them locally, and compares daily signals with a recent baseline.
KotlinJetpack ComposeFastAPISQLite
08 / Apps & Tools
PAL Evaluation
A volunteer reporting and cohort evaluation pilot with role-based access, session reports, attendance summaries, dashboards, and CSV exports.
JavaScriptSupabasePostgreSQLRLS
09 / AI & Data
English Audio Transcription (Wav2Vec2)
An English speech transcription script using pretrained Wav2Vec2, audio resampling and normalisation, and optional GPU inference.
PythonPyTorchHugging FaceASR
Test the model. Test the system.
The quality practices that surround the pipeline, from individual transforms to deployed services.
ML Model Unit Testing
Pytest-based suites for data preprocessing transforms, feature engineering functions, and model inference outputs.
Pipeline Integration Testing
Integration tests for data ingestion, model training, evaluation thresholds, and artifact storage in isolated environments.
Model Serving E2E Tests
Smoke and contract tests against deployed REST endpoints, checking latency, response schemas, and model output distributions in staging.
Load & Stress Testing
Locust and k6 tests against inference APIs, measuring throughput and p95 latency under realistic traffic patterns.
Explore the repositories.
Browse public projects by language, name, or topic.
Public repositories are also available on GitHub.
Explore the source.
Public repositories load here when available. You can also browse the full collection directly on GitHub.
Visit my GitHub profileHave an idea?
Start a conversation