# Hirundo

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

Hirundo provides a machine unlearning platform that surgically removes risky knowledge and behavior from trained large language models at the model level, without retraining. The service is aimed at AI and product teams, security and privacy teams, and frontier AI labs that need to mitigate jailbreaks, hallucinations, bias, and memorized PII in production models. It enables enterprises to fix model risks quickly, reducing launch delays and improving compliance.

## Kin Score — 11.7 / 100 (emerging)

Scored 2026-10-31 under rubric 0.25.0.

| Facet | Score |
|---|---|
| Discoverability | 39.3 |
| Contract Quality | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 0.0 |
| Developer Ergonomics | 19.0 |
| Access Clarity | 21.1 |

Regulatory layer — **Horizontal (data, software, accessibility, platform)**: 13.7 (matched via fallback).

## 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 |
| Delegated Identity | no |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| Agentic Commerce | no |
| Pagination Ratio | na |
| Operation Distinctiveness | na |

## Security (1)

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

## Tags

Machine Unlearning, AI Safety, Model Security, Data Privacy

---

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