Engineering deep dives, industry perspective, implementation notes, and practical recipes.
Search covers titles, summaries, tags and full article text.
KDCube separates the record that reloads a hosted conversation from the content rows that make it discoverable by semantic, lexical, and trigram search. This article maps both contracts — including the exact LangGraph, Claude Code, and native KDCube ReAct agent projections in use today.
KDCube now prepares every app under its own supervised lifecycle. A slow checkout, hook, index, or UI build makes that app temporarily unavailable without making an otherwise healthy processor look dead.
KDCube's ordered conversation lane now reaches agents that own their own loop. Followups and stop take effect at boundaries each runtime can safely expose, while anything not read remains ordered for the next turn.
A vector is a pure function of query, model and dimension — so every repeated search re-pays for an answer the system already has. The obvious fix is to remember it on the index object, and in a runtime where turns hop between workers it catches the one repeat that rarely happens. What the shared cache needs instead: a key that carries the model, a value ...
A teammate opens a browser, asks the resident agent to change a file in a git-backed store, watches the work happen as steps, reviews the diff on a desk beside the chat, and commits — under their own identity, with only the capabilities they granted.
Your app publishes a service. Discovery indexes it. An agent asks for it — and gets an error about a permission nobody has heard of. Nothing is broken: three of the four decisions that make a service usable have not been taken yet, and each belongs to someone else.
Run multiple websites locally on one KDCube, route each by alias or host, and expose the same routes through ngrok.
How KDCube apps choose among local operations, named services, Data Bus, jobs, conversation ingress, MCP, REST, and widgets.
Configure API, MCP, and widget enablement, visibility, auth, and API CSRF from code defaults, descriptors, or the Apps dashboard.
A production AI app is not one runtime. A single request can touch a webhook handler, scheduler, agent turn, app venv, networkless executor, provider app, and remote task. Each crossing carries only what its target should receive.
A hosted agent does not carry a session, restore a conversation, keep a file, or survive a worker restart on its own. Two different memories do that for it — one the platform owns, one the agent owns — and the line between them is the whole story.
An agent loop can choose a next action. It cannot, by itself, bind a user identity, serialize concurrent messages, preserve files, restore a conversation on another worker, enforce a grant, account for a model call, or isolate generated code. KDCube supplies that operating layer around the agent — without requiring the agent's reasoning core to become a K...