Hirundo

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.

Hirundo is profiled on the APIs.io network. Tagged areas include Machine Unlearning, AI Safety, Model Security, and Data Privacy.

Hirundo’s developer surface includes engineering blog, documentation, and 8 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

11.7/100 emerging Agent 0/100 human only Full breakdown ↓
scored 2026-10-31 · rubric v0.25.0 · Show this score on your site →

0 APIs

Machine UnlearningAI SafetyModel SecurityData Privacy

Kin Score

Kin Score How this is scored →
scored 2026-10-31 · rubric v0.25.0

Composite quality — 11.7/100 · emerging

Contract Quality 0.0 / 21

Developer Ergonomics 3.2 / 17

Access Clarity 3.6 / 17

Operational Transparency 0.0 / 11

Contract Governance 0.0 / 10

Discoverability 3.3 / 9

Regulatory Posture 2.1 / 15

Agent readiness — 0/100 · human only

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 0 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Pagination 5 / 5

Distinct Operations 3 / 3

Regulatory Posture applies to this provider. Its tags matched the Horizontal (data, software, accessibility, platform) regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.

Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.

The six quality facets above are damped to 85 points between them, because the conditional facet above carries the other 15. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 85% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Show this score on your site.

It updates itself when the score changes. Paste this where you link to your API docs:

<a href="https://apis.io/providers/hirundo/"><img src="https://apis.io/badge/hirundo/card.svg" alt="Hirundo on APIs.io — Kin Score by API Evangelist"></a>

Other styles, a README pill and a shields.io endpoint are on the badge page.

Raise your score.

Agent readiness — checks not met, largest first (exact, from this profile):

Machine-Readable Contract +18 pts — api_specs includes an OpenAPI document
MCP Server +12 pts — deployment.mode + probe verdict on the mcp/ manifest, not the pointer; an unprobed slug falls back to authorship
Agentic Access Contract +10 pts — agentic_access artifact present (x-agentic-access), graded by author
Machine-Readable Auth +10 pts — a served openid-configuration/oauth-authorization-server carrying `issuer` (served), else the securitySchemes class in the provider OpenAPIs — bound (mutualTLS, DPoP, Signature) > negotiable (oauth2 authorizationCode/clientCredentials, openIdConnect) > bearer (http bearer, apiKey)
Idempotency +9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
A2A Agent Card +8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0

13 more unmet checks in the Agent Readiness table above.

Kin Score — facets with the most composite points still available (weight × headroom):

Contract Quality scores 0.0 — up to +25.0 composite points
Developer Ergonomics scores 19.0 — up to +16.2 composite points
Access Clarity scores 21.1 — up to +15.8 composite points

Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from the provider profile at artifacts.apis.io/hirundo/apis.yml: open an issue on github.com/api-evangelist/hirundo to ask a question or point us at an artifact you publish. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Security Posture 1

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Hirundo Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Resources

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Build 2

SDKs, sample code, and the tooling you integrate with

SDKs

SDKs

Packages

Packages

Access & Security 1

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Commercial 2

Pricing, plans, and the legal terms of use

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 2

The organization behind the API

Blog

Blog

Website

Website

Other 2

Properties that don't map to a standard resource type

Hosts

Hosts

Vendors

Vendors

Source (apis.yml)

aid: hirundo
name: Hirundo
image: https://cdn.prod.website-files.com/660ac5137d0f7fda07d7ce65/6612706c7c1f0f80e8973596_Hirundo%20OpenGraph%20Image.png
description: 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.
url: https://raw.githubusercontent.com/api-evangelist/hirundo/refs/heads/main/apis.yml
x-type: company
x-source: harvest:g2-catalog
x-tier: profiled
x-tier-reason: enrichment pass 2026-10-20 (modular-v1; was harvest)
specificationVersion: '0.20'
created: '2026-10-20'
modified: '2026-10-20'
tags:
- Machine Unlearning
- AI Safety
- Model Security
- Data Privacy
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Hosts
  url: hosts/hirundo-hosts.yml
- type: Vendors
  url: vendors/hirundo-vendors.yml
- type: SDKs
  url: packages/hirundo-packages.yml
- type: Packages
  url: packages/hirundo-packages.yml
- type: TermsOfService
  url: https://www.hirundo.io/tos
- type: PrivacyPolicy
  url: https://www.hirundo.io/privacy-policy
- type: Blog
  url: https://www.hirundo.io/blog
- type: Documentation
  url: https://docs.hirundo.io/
- type: DomainSecurity
  url: security/hirundo-domain-security.yml
- type: Website
  url: https://hirundo.io/
apis: []
x-coverage:
  state: none
  reason: no-developer-program
  method: derived
  generated: '2026-10-20'
  generator: derive-coverage.py (pre-flight evidence)
  detail: the company publishes no developer documentation host and no machine-readable contract on its own domain
  evidence:
  - url: https://hirundo.io/
    status: 200
x-enrichment:
  date: '2026-10-20'
  status: enriched
  artifacts_added: 7
  pass: modular-v1
  engine: identity=local,contract=local,surfaces=local,docs=local,regulatory=local

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/hirundo"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/hirundo/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/hirundo/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.