HAPI MCP
Turn API contracts into tools that AI systems can actually use.
Visit projectLa Rebelion Labs is where stubborn questions become useful software. We explore AI, APIs, and developer infrastructure—then ship the tools we wish already existed.
AI systemsAPI craftTools for buildersThe status quo is useful—right up until it becomes invisible. We make assumptions visible, test them in public, and turn the useful discoveries into products.
Independent products, open tools, and experiments sharing one point of view.
Explore every projectTurn API contracts into tools that AI systems can actually use.
Visit projectA local-first voiceover workspace built for scripts that keep changing.
Visit projectA sharper workbench for designing, testing, and shipping APIs.
Visit projectArchitecture, AI, APIs, and the uncomfortable work of making systems better.
Browse the archive
Eight AI and agentic systems signals from October 15–21, 2026, and three practical experiments for safer harnesses, durable state, and verifiable outcomes.

The model is the engine, the harness is the car. We sort today's AI coding tools into six families, map them onto your software lifecycle, and share a practical way to choose.

How engineers can maintain their value and professional identity in the age of AI.

Measure and cut the tokens Reverse Engineering Anything puts in your AI agent's context, keep agents working while big binaries decompile, and see which optimizations are still open proposals.

A hands-on course on Spec-Driven Development with AI coding agents. Learn the theory, set up OpenSpec, and build a tested MVP in three small changes.

Learn what ClickHouse is, why it is fast, when to use it, and how to load 100 million rows and answer a dashboard question in about a third of a second.

Connect REA to your AI coding agent, trace a real app feature from a button to the code that runs it, and check every claim against evidence you can verify yourself.

Learn how to effectively build an AI harness to maximize the value of AI models and create reusable systems.

AI models are rapidly commoditizing. The real advantage now is AI orchestration: memory, verification, safety guardrails, and workflow design. Learn a practical framework to build reliable AI systems.