# Cloud World Model Platform

Cloud World Model is a multi-cloud infrastructure simulation platform that lets developers, architects, and AI agents practice and test cloud infrastructure designs without provisioning real resources - and without cloud bills.

> Simulate the cloud without the cloud. Predict behavior, analyze cost and resilience, and train reinforcement learning agents across AWS, GCP, Azure, OCI, and DigitalOcean - all in a safe, cost-free environment.

## Product

- **What it is**: A Canvas Cloud AI companion product providing a realistic cloud simulation engine for hands-on practice and AI agent training.
- **Primary audiences**: Cloud architects and learners who want to practice without AWS/GCP/Azure bills; AI/RL researchers who need a safe environment to train autoscaling and optimization agents.
- **Cloud providers supported**: AWS, Google Cloud (GCP), Microsoft Azure, Oracle Cloud (OCI), DigitalOcean.
- **Key capabilities**: Capacity-aware simulation, autoscaling, chaos engineering, multi-cloud strategy exploration, predictive scaling, cost analysis, and AI-generated explanations.

## Pages

- [Home](https://www.cloudworldmodel.ai/) - Platform overview and getting started
- [Getting Started](https://www.cloudworldmodel.ai/getting-started) - Quickstart guide for new users
- [Simulation API Walkthrough](https://www.cloudworldmodel.ai/simulation-walkthrough) - End-to-end tutorial chaining all core simulation API calls in sequence
- [Use Cases](https://www.cloudworldmodel.ai/use-cases) - Example use cases for learners and AI agents
- [Workspace](https://www.cloudworldmodel.ai/workspace) - Visual canvas for building and simulating cloud architectures
- [Scenarios](https://www.cloudworldmodel.ai/scenarios) - Pre-built and saved simulation scenarios
- [Agents](https://www.cloudworldmodel.ai/agents) - RL agent dashboard and API key management
- [Pricing](https://www.cloudworldmodel.ai/pricing) - Free tier, credit packs, and cost per API call
- [Pricing History](https://www.cloudworldmodel.ai/pricing-history) - Historical cloud provider pricing data
- [Billing](https://www.cloudworldmodel.ai/billing) - Credit balance and top-up
- [Simulation Fidelity](https://www.cloudworldmodel.ai/fidelity) - Benchmark sources and accuracy ranges for every simulated metric (±10% cost, ±15% performance)
- [Supported Regions](https://www.cloudworldmodel.ai/regions) - All cloud regions supported by the simulator across AWS, GCP, Azure, OCI, and DigitalOcean — with zone counts and locality type details
- [Benchmark Report](https://www.cloudworldmodel.ai/benchmark) - Full multi-cloud pricing and performance benchmark report comparing AWS, GCP, Azure, OCI, and DigitalOcean
- [Simulation Accuracy Benchmark](https://www.cloudworldmodel.ai/accuracy) - Side-by-side comparison of simulated vs. AWS reference metrics for a 3-tier architecture across Idle/Normal/Peak/Burst traffic scenarios
- [RL Training Environments](https://www.cloudworldmodel.ai/rl/environments) - Reference guide for training reinforcement learning agents against the cloud simulator: episode lifecycle, action space, observation vector, reward signal, and Python quickstart. Runnable multi-episode training-loop examples: Python (`examples/rl_training_loop.py`), JavaScript (`examples/rl_training_loop.js`), Fetch API (`examples/rl_training_loop_fetch.mjs`), TypeScript (`examples/rl_training_loop.ts`), Go (`examples/rl_training_loop.go`, stdlib only — `go run examples/rl_training_loop.go --token $API_KEY`).
- [Provider Coverage](https://www.cloudworldmodel.ai/provider-coverage) - Every service, instance size, and pricing model the simulator covers for AWS, GCP, Azure, OCI, and DigitalOcean — counts and base rates derived from the live pricing constants
- [Privacy Policy](https://www.cloudworldmodel.ai/privacy) - Privacy policy
- [Terms of Service](https://www.cloudworldmodel.ai/terms) - Terms of service
- [Blog](https://www.cloudworldmodel.ai/blog) - TODO: add description
- [Blog/What We Learned Product Hunt](https://www.cloudworldmodel.ai/blog/what-we-learned-product-hunt) - Retrospective on the Product Hunt launch: key takeaways from finishing #5 Product of the Day and 100+ user comments
- [Blog/X402 Cloud Simulation Api](https://www.cloudworldmodel.ai/blog/x402-cloud-simulation-api) - How we built native x402 payable API support so AI agents can run simulations and pay per request — no human-in-the-loop billing setup required.

## x402 Payment Support

Cloud World Model supports the **x402 pay-per-request protocol** (a Linux Foundation project). AI agents can call any of the 14 metered API endpoints without creating an account or managing an API key — pay per call in USDC on the Base network.

- **Discovery endpoint**: `GET https://www.cloudworldmodel.ai/api/billing/x402/config` — returns the enabled flag, payTo wallet address, network (`base`), USDC asset address, facilitator URL, and per-call-type price table.
- **Agent-facing OpenAPI subset**: `GET https://www.cloudworldmodel.ai/.well-known/x402/openapi.json` — curated OpenAPI spec covering the 14 paid endpoints plus selected free lifecycle routes (observation GET, reset POST, RL environment CRUD).
- **14 paid call types** ($0.0010 each: `simulation_step_hybrid`, `rl_step`, `rl_batch_step`, `rl_eval_episodes`, `ai_explain`, `ai_optimize`, `ai_troubleshoot`, `ai_bottleneck`; $0.0050 each: `chaos_run`, `chaos_batch`, `multicloud_explore`, `optimization_run`, `prediction_validate`, `prediction_optimize_thresholds`).
- **Network**: Base (Ethereum L2)
- **Asset**: USDC
- **No signup required**: attach an `X-PAYMENT` header and call any metered endpoint directly.
- **Balance & history**: `GET /api/billing/x402/balance?address=0x...` and `GET /api/billing/x402/transactions?address=0x...`
- **x402scan listing**: https://www.x402scan.com/server/1a8052f0-c764-420a-96a5-f50d3c696795 — browse and call all metered endpoints directly from the x402scan discovery index.

## API

- [RL Training API](https://www.cloudworldmodel.ai/agents) - RESTful API for reinforcement learning agents to interact with the autoscaling simulator; supports episode lifecycle, multi-objective rewards, and secure API key auth. `POST /rl/environments/{id}/batch-step` accepts up to 30 actions per request (each counts as 1 call against the 5 000 req/hr RL quota) and returns an array of step results, stopping early when the episode ends. All 429 responses include a `Retry-After` header with the exact seconds until the window resets. The `add_resource` step action accepts AWS database targets including `aurora-postgresql`, `aurora-dsql`, and `aurora-serverless` (Aurora Serverless v2, scales ACUs with load). See `llms-full.txt` for a complete Python episode-loop quickstart showing how to handle the 2–4 step ACU ramp delay and read steady-state `cost_usd_hr` after the resource reaches operating capacity.
- [Chaos Engineering API](https://www.cloudworldmodel.ai/agents) - Inject failures (database crash, zone outage, network partition) and receive resilience scores and remediation recommendations. Aurora Serverless v2 (`aurora-serverless`) is a valid `database_crash` / `database_slowdown` target alongside RDS and provisioned Aurora; after a `database_crash` the result models a 2–4 step ACU warm-up before full throughput resumes.
- [Multi-Cloud Strategy API](https://www.cloudworldmodel.ai/agents) - Generate and compare multi-cloud architecture variants with cost, latency, and vendor lock-in analysis. When exploring AWS-anchored strategies, use `serviceFamily: "aurora-serverless"` to include Aurora Serverless v2 as a cost-aware database candidate — it scales ACUs with load rather than being fixed at peak provisioned size, and typically produces a lower `cost_usd_hr` estimate than equivalent provisioned `aurora-postgresql` variants (e.g. ~$0.09/hr vs ~$0.15/hr for a variable workload at average load); note: ACU ramp-up from near-zero can add 1–5 s of latency on the first request after an idle period — avoid this option for latency-sensitive workloads that cannot tolerate cold-start delays.
- [Predictive Scaling API](https://www.cloudworldmodel.ai/agents) - Validate infrastructure against traffic forecasts and optimize autoscaling thresholds.
- [Webhook/Callback System](https://www.cloudworldmodel.ai/agents) - Asynchronous job completion notifications via HMAC-signed HTTPS callbacks.
- [Simulation Events API](https://www.cloudworldmodel.ai/agents) - Annotate or clear a simulation's event log: POST /simulations/{id}/events injects a manual annotation; DELETE /simulations/{id}/events clears all events.
- [Simulation Claim API](https://www.cloudworldmodel.ai/agents) - Assign ownership of an unowned (demo) simulation to your API key: POST /simulations/{id}/claim transfers a keyless simulation to the authenticated caller, enabling unlimited steps and full write access. Returns 409 if already owned by another key.
- [Simulation Snapshot API](https://www.cloudworldmodel.ai/agents) - Single-call run object for external tools: GET /simulations/{id}/snapshot returns a versioned JSON envelope with architecture, latest metrics, active failures, last 10 significant events, and _links to detailed endpoints — no stitching required. schemaVersion stays at 2. POST /simulations/{id}/snapshots pins the current state and returns a `pinnedSnapshotId`; pass it as `?since=<pinnedSnapshotId>` to GET /snapshot to receive a `diff` block showing architecture adds/removes, metric deltas (from/to/delta), failure changes, and recommendation changes since the pin.

## WebMCP Browser Tools

AI agents navigating the site in a WebMCP-enabled browser (Chrome with `navigator.modelContext`) can invoke these tools directly on any page:

- `run_simulation_step` — Advance the active simulation by one tick and return the updated metrics snapshot.
- `reset_simulation` — Pause the active simulation and reset traffic to zero.
- `inject_traffic_pattern` — Inject a named traffic pattern (ramp, burst, step, wave, custom) into the running simulation. Legacy aliases spike→burst, sine→wave, gradual_increase→ramp are also accepted.
- `inject_failure` — Inject a named failure type (database_crash, zone_outage, network_latency, instance_kill) into the running simulation.
- `inject_failure_create` — Create a scheduled failure injection (POST /simulations/{id}/failures): type (instance_kill, az_outage, database_overload, network_latency), start/end steps, optional target. Requires write scope or wallet JWT.
- `inject_failure_update` — Update an existing failure injection (PATCH /failures/{id}): deactivate early or change end time. Requires write scope or wallet JWT.
- `inject_failure_delete` — Permanently delete a failure injection (DELETE /failures/{id}). Returns 204. Requires write scope or wallet JWT.
- `get_current_metrics` — Read the latest CPU, latency percentiles, error rate, throughput, and estimated cost for the active simulation.
- `navigate_to_page` — Navigate the browser to a named platform page (home, scenarios, billing, docs, api-reference).

All tools accept an optional `simulationId`; if omitted they use the simulation currently open in the browser. All tools are no-ops in browsers without `navigator.modelContext`.

## Docs

- [llms-full.txt](https://www.cloudworldmodel.ai/llms-full.txt) - Extended reference for AI tools: full API endpoint list, provider coverage, pricing details, and integration notes.
- [Sitemap](https://www.cloudworldmodel.ai/sitemap.xml) - XML sitemap of all public pages.