Bundles — the unit of an AI app
One folder packages backend logic, APIs, widgets, full UI, agents, tools, storage, secrets, and cron. Hot-reloadable; deploy without restarting the runtime.
Bundle docs →What is KDCube
The environment your agents live in.
A self-hosted Python platform where your agents live, the tools they need plug in, and the surfaces that expose them — chat widgets, copilots, smart APIs, scheduled pipelines, dashboards, MCP — share one runtime for tenancy, budgets, governance, and observability. Our mission: KDCube is the easiest way to run AI apps in your organization.
Per-environment isolation
A tenant/project is a full environment with its own descriptors, secrets, Postgres schema, and Redis. Stage, customer segment, or team — each gets a clean boundary.
Many surfaces, one bundle
Chat widgets, embedded UIs, REST endpoints, iframe apps, MCP servers, and @cron jobs all in one bundle. The default answer to "where does this AI feature live?"
Pluggable agent runtimes
Ship with ReAct v2 (timeline-first) and Claude Code (workspace-bound). Or bring your own inside a bundle — LangGraph, CrewAI, plain Python.
ReAct v2 docs →Built-in economics
Per-tenant, per-customer, per-turn cost accounting. Hard spend caps reserved before each turn. Stripe-integrated wallets and an exportable ledger.
Economics docs →Decision provenance
Every turn is a replayable timeline artifact: sources, plan, tool calls, costs. Replay why an agent did what it did, end-to-end, without scraping logs.
Timeline docs →From prototype to production — on infrastructure you own.
How it works →