# Simular

**Canonical:** https://apis.io/providers/simular/  
**Website:** https://simular.ai  
**APIs profiled:** 0

Simular is the autonomous computer company. It builds AI agents that operate computers the way people do — clicking, typing, scrolling, and navigating GUIs, APIs, terminals, and code. Its flagship product Sai is a 24/7 AI co-worker that runs on private cloud desktops, and it maintains the open-source Agent-S agentic framework, the OpenACI agent-computer interface, and Simulang, a desktop-automation scripting language with Python (pysimular), Node.js (@simular-ai/simulang-js), and CLI (@simular-ai/simulang) surfaces. Developers integrate Simular through these SDKs and a Claude Code /simulang skill rather than a hosted HTTP API. Simular is backed by Felicis.

## Kin Score — 23.6 / 100 (emerging)

Scored 2026-08-19 under rubric 0.12.0. Trend: flat (-1.8 from 25.4).

| Facet | Score |
|---|---|
| Discoverability | 57.4 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 2.6 |
| Developer Ergonomics | 66.7 |
| Commercial Clarity | 21.1 |
| Access Clarity | 21.1 |

## Agent readiness — 4.3 (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 | yes |
| 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)

- **Simular Domain Security** — TLSv1.3 · HSTS · DNSSEC · DMARC

## Tags

Company, Artificial Intelligence, AI Agents, Computer Use, Browser Automation, Desktop Automation, Agentic, SDK, Developer Tools, Open Source

---

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