# Over

**Canonical:** https://apis.io/providers/over/  
**Website:** https://over.world/  
**APIs profiled:** 0

Overworld is an open-science AI research lab building interactive world models - AI-generated video environments that respond in real time to text prompts and controller input at game-level framerates. Its open-source World Engine is a Python inference library that loads Waypoint world models and LoRA adapters from HuggingFace to generate playable, promptable worlds locally or in the browser. Founded by Louis Castricato (CEO) and Shahbuland Matiana (Head of Mathematical Research), both formerly of CarperAI and Stability AI, the team operates openly and publishes its infrastructure as public open-source repositories. Overworld does not currently expose a hosted REST API; its primary developer artifact is the first-party world_engine Python SDK.

## Kin Score — 15.8 / 100 (emerging)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 15.8).

| Facet | Score |
|---|---|
| Discoverability | 57.4 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 2.6 |
| Developer Ergonomics | 38.1 |
| Commercial Clarity | 10.5 |
| Access Clarity | 10.5 |

## Agent readiness — 0.0 (human-only)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | no |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Unknown — onboarding: unknown, pricing: unknown, trial: no (confidence: low).

## Security (1)

- **Over Domain Security** — TLSv1.3 · HSTS · DMARC

## Tags

Company, Artificial Intelligence, World Models, Generative AI, Video Generation, Gaming, Machine-Learning, SDK, Python

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/over/). Scores are computed from the provider's own public artifacts under a published rubric.