# Heyclicky

**Canonical:** https://apis.io/providers/heyclicky/  
**Website:** https://heyclicky.com/  
**APIs profiled:** 0

Heyclicky (product name Clicky) is a consumer macOS application from the Y Combinator Spring 2026 batch that puts an AI assistant right next to your cursor. In Talk Mode a hotkey lets you ask about whatever is on screen and get spoken, on-screen guidance; in Agent Mode you can command autonomous agents to build, research, or perform tasks in the background, and it can connect to services like Notion, Gmail, and Calendar. The app is screen-aware, works across any application with no plugins, and ships as a notarized macOS binary distributed via a Sparkle appcast on GitHub. Heyclicky is a consumer desktop product; it does not currently publish a public developer API, SDK, or OpenAPI surface.

## Kin Score — 11.0 / 100 (emerging)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 11.0).

| Facet | Score |
|---|---|
| Discoverability | 50.0 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 2.6 |
| Developer Ergonomics | 4.8 |
| Commercial Clarity | 23.7 |
| Access Clarity | 23.7 |

## 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)

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

## Tags

Company, Artificial Intelligence, Assistant, macOS, Desktop, Productivity, Agents, Consumer, Y Combinator

---

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