KDCube — Semantic Sandbox for Enterprise AI Agents

Infra Sandbox

What it does: Isolates execution environment

What it misses: Does not know what the agent intended to do

Guardrails Wrapper

What it does: Filters output after generation

What it misses: Does not intercept tool calls or API actions

Observability Tool

What it does: Logs what happened

What it misses: Logs are read after the fact — damage already done

Traditional Sandbox

Isolates where code runs. Controls the compute environment. Does not understand what the agent is trying to do.

Semantic Sandbox

Controls what an agent is permitted to do — based on intent, context, and policy — before any action is taken.

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, per-org spending caps
• Hard limits that cannot be overridden
• 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
• Knowledge base / memory context patterns

✅ 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

Block before execution — not after

Most tools observe or filter. KDCube intercepts. The enforcement decision happens before any external system is called. Wrong actions do not execute.

Semantic constraints, not just compute limits

Rate limits and memory caps are infrastructure. KDCube enforces what the agent is allowed to do — action scope, data access, spend authority — not just how much CPU it uses.

Self-hosted. Your infrastructure, your policy.

KDCube runs on your infrastructure. No vendor has access to your agent interactions, your policies, or your data. MIT licensed. No lock-in.

Open-source and auditable

The enforcement layer is not a black box. Every constraint, every decision, every blocked action is logged and inspectable. You own the audit trail.

Deploy in under 30 minutes

git clone https://github.com/elenaviter/kdcube-ai-app
cd kdcube-ai-app/app/ai-app/deployment/docker/all_in_one

# Setup directories
mkdir -p data/{kdcube-storage,exec-workspace,postgres,redis,clamav,neo4j/{data,logs,plugins,import}}
chmod -R 0777 data
mkdir -p logs/{chat,kb,dramatiq} nginx/webroot

# Build code execution image
docker build -t py-code-exec:latest -f Dockerfile_Exec ../../..

# Initialize database
docker compose build postgres-setup
docker compose run --rm postgres-setup

# Add API key to .env.backend:
# ANTHROPIC_API_KEY=sk-ant-api03-your-key

# Start services
docker compose build && docker compose up -d

# Runtime ready at localhost:8000

Quick setup: pipx install kdcube-apps-cli && kdcube-apps-cli

What you get

• Deploy in under 30 minutes — Docker Compose, single command
• 60–80% lower infrastructure cost vs. managed SaaS agent platforms (estimated, based on typical SaaS pricing vs. self-hosted infrastructure costs)
• Your data stays on your infrastructure — no calls home, no telemetry you did not configure

KDCube is MIT licensed. The full source is on GitHub. Deploy on your own infrastructure — a single VPS, Docker Compose, or a Kubernetes cluster — and you control everything.

No usage-based fees. No per-seat pricing. No vendor access to your agent traffic. Infrastructure costs vary by cloud provider and configuration; example ranges of $50–$2,000/month are based on typical VPS/cloud pricing. The runtime itself is free.