KDCubesafer way to build AI

Empower your customers with an AI assistant.
Self-hosted, multi-tenant platform with SDK for building trustful AI assistants, copilots, and agentic apps with control, provenance and auditability.

  • ReAct v2 Timeline-First Agent — structured turn memory with provenance by default
  • Multi-tenant by design — tenant isolation enforced across gateway, storage, and budget accounting
  • Channeled streaming + live widgets — SSE/Socket.IO fan-out with dynamic bundle UIs

For architecture and control details, see Docs and Security.

Star on GitHub MIT License Self-Hosted Open Source

Agent-First #

ReAct v2 Timeline-First Agent is the KDCube signature. No tool-calling framework lock-in — bring your own tools or use the SDK.

Economic Accounting #

Usage, budgets, and rate limits tracked per user, project, and organization. Hard limits enforced outside prompt logic.

Multi-Tenant Platform #

Tenant separation enforced across request routing, storage, and accounting. Host copilots for multiple customers on one stack.

Self-Hosted & Open Source #

Docker Compose quickstart. Deploy on EC2, ECS/Fargate, or Kubernetes. MIT License. No vendor data path required.

Infrastructure sandboxing is not enough #

Compute isolation is necessary, but companies also need policy, spend, and tenant controls before actions are executed.

Infrastructure sandboxing

Good at isolating compute and limiting process-level access.

Not enough for business controls like approval policy, tenant scope, and cost containment.

What KDCube adds

  • Action mediation: privileged operations pass through controlled runtime boundaries.
  • Cost governance: spend and rate controls are enforced independently of prompt output.
  • Tenant enforcement: request and data access paths are scoped by tenant and project.
  • Auditability: decisions are traceable on infrastructure you control.

The enterprise risk is policy failure, not only process escape. KDCube focuses on preventing unsafe or out-of-scope actions before they execute.

How KDCube works #

Admit, enforce, execute, and audit. Implementation detail is in Docs.

Subprocess-isolated code execution #

  • Isolated subprocess within Docker Compose deployment
  • No external network access by default
  • Sensitive env vars stripped; minimal filtered environment; workdir filesystem only

✅ Available

Budget controls and rate limiting #

  • Per-user, per-project, and per-org spending caps with multi-tier accounting rollups
  • Reservation/commit economics checks at admission with hard-limit enforcement
  • Request frequency and token throughput constraints

✅ Available

Multi-tenant isolation patterns #

  • Tenant boundary validated on every request
  • Cross-tenant DB access blocked at the gateway layer
  • Knowledge base scoping per tenant (validate KB isolation boundaries during setup)

✅ Available

Streaming runtime with tool orchestration #

  • REST, SSE (Server-Sent Events), Socket.IO
  • Token-by-token streaming responses
  • Composable Skills and tool namespaces (local + MCP) via dynamic bundles

✅ Available

Decision logging (request/response) #

  • Every allow/block decision timestamped
  • Self-hosted on your infrastructure
  • Control plane monitoring dashboard included

✅ Available

Policy DSL & deterministic enforcement Roadmap #

  • Declarative constraint definitions per agent role
  • Verifiable allow/deny before any tool call fires
  • Workflow invariants and cross-agent approval gates

🔮 Roadmap

Where runtime enforcement matters #

Enterprise scenarios where pre-execution control is required.

Refund Authorization

KDCube enforces a maximum refund per transaction. Requests above the limit require human approval.

$500 hard cap enforced

CRM Access Boundaries

KDCube enforces tenant boundaries at the gateway layer, blocking cross-tenant access before it reaches the database.

Zero cross-tenant leaks

Approval Workflows

Agents can draft contracts, while approval-gated final actions remain controlled. Explicit workflow-step invariant gating is roadmap.

Enforced approval gates Roadmap

Data Boundary Enforcement

KDCube restricts outbound API calls to an approved allowlist. Unapproved endpoints are blocked, and execution has no external network access by default.

Allowlist-only outbound calls

Cost Containment

KDCube enforces per-user, per-project, and per-org spending caps so hard limits cannot be exceeded.

Potential 60–80% infra savings in self-hosted scenarios*

Secure Code Execution

KDCube runs agent-generated code in an isolated subprocess with no external network access and no environment variable access by default.

Zero network egress by default

*Estimate range depends on workload profile, model mix, traffic shape, and infrastructure/operations choices.

Why KDCube #

Seven differentiators that define the platform — sourced from README Highlights.

Full stack #

UI + backend + SDK + ops tooling shipped together. One cohesive platform, not a stitched pipeline.

Agent-first #

ReAct v2 Timeline-First Agent is the KDCube signature. No tool-calling framework lock-in.

Multi-tenant #

Isolation enforced across request routing, storage, and economic accounting. Host copilots for multiple customers.

Provenance by default #

Every source, tool call, and citation is tracked in the timeline. Perplexity-style traceability built-in.

Channeled streaming #

SSE/Socket.IO fan-out with typed event channels. Live bundle UIs and role-based event filtering.

Feedback-aware #

User and system feedback events captured in the timeline for evaluation and model improvement loops.

Open-source and self-hosted #

Fast evaluation path #

Use the all-in-one deployment to validate fit quickly, then move to managed infra patterns for production.

  • Typical first environment in under an hour
  • Clear migration path to production topology
  • Full setup steps in Deployment Model

What you get #

  • Business-safe defaults for spend, tenant separation, and controlled execution
  • Deployment flexibility across VPS, Docker Compose, and Kubernetes
  • Data stays in your environment by default

KDCube is MIT licensed and fully open source on GitHub. Deploy on your own infrastructure and operate with your own controls.

No runtime license fee. Your costs are infrastructure and model usage, which vary by deployment size and provider.

Where we are headed #

The current runtime already provides economic controls, isolation, and Observability signals (monitoring endpoints, queue pressure, circuit-breaker state) used for scaling decisions. The following items are additional roadmap capabilities and are not yet shipped.

Policy DSL Roadmap

Declare agent permissions in a human-readable policy language. Define what actions, data scopes, and spend limits are permitted per agent role.

Deterministic Enforcement Engine Roadmap

Pre-execution evaluation that produces a verifiable allow/deny decision before any tool call fires, with no probabilistic components.

Workflow Invariants Roadmap

Declare required steps in a workflow. Prevent agents from skipping approval gates, notification steps, or compliance checkpoints.

Cross-Agent Approval Gates Roadmap

Require a second agent, human-in-the-loop confirmation, or external approval before high-impact actions execute.

Follow progress: github.com/kdcube/kdcube-ai-app

KDCube vs. the Alternatives #

KDCube is the only self-hosted agentic runtime with built-in multi-tenant policy enforcement, per-tenant economics, and dual-protocol streaming — no cloud lock-in required.

Feature comparison: KDCube vs. LangGraph Platform vs. CrewAI vs. AutoGen vs. OpenAI Assistants API vs. AWS Bedrock Agents vs. Vertex AI Agent Engine vs. AgentScope Runtime (March 2026). ✅ = native built-in; Partial = partially available or cloud-only; ✗ = not natively available; ❓ = unclear.
Feature KDCube self-hosted runtime LangGraph Platform stateful graph exec CrewAI multi-agent orch. AutoGen / AG2 MS multi-agent OpenAI Assistants cloud-hosted runtime AWS Bedrock Agents cloud-hosted runtime Vertex AI Agents GCP cloud runtime AgentScope Runtime distributed multi-agent
Pre-execution policy gate Partial Partial
Per-tenant budget caps & rate limits Partial
Tenant boundary isolation Partial Partial Partial
Subprocess / sandbox isolation Partial Partial Partial Partial Partial
Audit trail & decision logging Partial Partial Partial
Real-time streaming (SSE + WebSocket) Partial Partial Partial Partial Partial Partial
Self-hosted / on-premises Partial
Open-source / auditable
Multi-protocol clients (REST + SSE + WS) Partial
Built-in knowledge base / RAG Partial Partial Partial
Token / cost accounting per tenant Partial Partial Partial
Multi-model routing (OpenAI + Anthropic + Gemini) Partial Partial
MCP tool integration Partial Partial Partial
Citation / provenance tracking Partial Partial Partial

Build AI that doesn't break trust

Deploy runtime controls in under an hour. Review the code, run it in your environment, and evaluate the enforcement layer directly.

MIT Licensed · Self-Hosted · Open Source