Questions, answered.

Norah Labs is an AI and full-stack engineering studio based in Nairobi, Kenya. We build production AI agents, web and mobile platforms and cloud infrastructure, with design, motion and communications handled by the same team. The studio was founded in 2021 by John Alexander Kamau.

Four services: AI engineering (LLM agents, RAG, evaluation and guardrails), full-stack web and mobile development, DevOps and cloud infrastructure, and creative and communications (brand identity, motion, 3D, video, campaigns and PR).

Norah Labs was founded by John Alexander Kamau, an engineer, designer and communications strategist who leads product, design and AI. Amariah Abishai is co-founder, a full-stack developer and DevOps specialist focused on scalable, reliable systems.

We are based in Nairobi, Kenya, and partner with clients globally, from startups and technical founders to growing companies and organizations modernizing their systems.

Tabibu Health, an AI health companion for Africa giving evidence-based answers in English and Swahili; Atlarix, a local-first, approval-gated agent workstation that won the Amazon Nova AI Hackathon and is used by 77 developers across 12 countries; and Teleios Connect, a church media app with offline access. TradeEdge / MerchIQ and a smart hotel access system are in progress.

Yes. We build LLM agents that use tools, retrieval-augmented generation (RAG) with source citations, and the evaluation, guardrails and monitoring around them. Tabibu Health, for example, uses LangChain and LangGraph with dual guardrails and emergency detection.

Use the contact form on norahlabs.com/contact or email norahlabs.hq@gmail.com with your goal, constraints and timeline. We typically respond within 24 hours with questions or a practical next step.

It depends on scope, so we do not publish fixed prices. Share what you are building and we reply with a practical plan covering approach, timeline and cost for your specific project.

Yes. Norah Labs is registered with the Office of the Data Protection Commissioner (ODPC) in Kenya. To confirm our registration certificate, contact us.

Retrieval-augmented generation (RAG) is a technique where a language model first retrieves relevant passages from a trusted knowledge source and then writes its answer from them, usually with citations. It reduces made-up answers and lets you update knowledge without retraining the model. Norah Labs builds RAG systems with source citations, as in Tabibu Health.

We build LLM agents that use tools, RAG systems grounded in your data, AI features inside existing products, custom machine-learning models, and the evaluation, guardrails and monitoring around them. Examples include Tabibu Health, an AI health companion, and Atlarix, a local-first agent workstation.

Hosted models such as OpenAI and Anthropic, open-weight models such as Llama, DeepSeek, Qwen, Kimi and MiniMax, and local models. We design systems so the model can be swapped without rewriting the product, so you are not locked in to one provider.

We build guardrails and safety checks into the first version, evaluate outputs before release, and place human approval gates where the stakes are high. After launch we monitor quality and tune the system as the data changes.

Yes. We integrate AI into existing systems rather than rebuilding them: a retrieval layer over your documents, an assistant inside your app, or an agent connected to your internal tools and APIs.

React, Next.js and TypeScript on the front end; Node.js and Python (including FastAPI) on the back end; React Native and Expo for mobile; and PostgreSQL, MongoDB, Supabase or Firebase for data. We pick the stack for the problem and for the team that will maintain it.

Yes. We build cross-platform mobile apps with React Native, so one codebase serves iOS and Android. Teleios Connect, a church media app with offline downloads, is built this way.

Yes. We modernize legacy systems with minimal disruption, planning the transition so operations continue while the new platform takes over.

Yes. We build MVPs on scalable foundations so the first version does not have to be thrown away as the product grows.

DevOps joins software development and operations so code moves to production quickly and safely. In practice that means automated CI/CD pipelines, infrastructure defined as code, monitoring and alerting, and clear incident response.

AWS, Google Cloud, Vercel, Railway and Fly.io. We choose by workload, team skills and cost, and use infrastructure as code (Terraform, Pulumi or AWS CDK) so environments are reproducible.

Yes. We plan migrations carefully, move workloads to modern cloud systems, and add the pipelines and monitoring needed to run them confidently.

Yes. We offer monitoring, maintenance and incident response so systems keep running after the initial build.

Brand identity and graphic design, motion graphics and animation, 3D design and visualization, video production and post, campaign and social design, and PR and communications strategy.

When the people who build the product also design its brand and tell its story, nothing is lost in handoffs. The interface, the motion, the launch video and the code are made to match.

Yes. Identity, video and communications work can be commissioned on its own, and many clients later add product engineering.