Mirai

Mirai (trymirai.com) is an on-device AI infrastructure company building uzu, a high-performance, Rust-based inference engine that runs large language, text-to-speech, and classification models directly on consumer hardware — Apple Silicon, iOS, macOS, and beyond — with zero inference cost and full data privacy. The uzu SDK exposes a single high-level API across Python, Swift, TypeScript, and Rust, adding speculative decoding, structured output, and built-in performance metrics, plus an optional cloud path for hosted models. Founded by the co-creators of Reface and Prisma and backed by a $10M seed round led by Uncork Capital.

Mirai publishes 1 API on the APIs.io network. Tagged areas include Company, Artificial Intelligence, On-Device AI, Inference, and LLM.

Mirai’s developer surface includes documentation, getting-started guide, signup flow, engineering blog, support, and 6 more developer resources.

🌐 Visit website 📡 Source on GitHub

22.5/100 emerging ▬ flat Agent 0/100 human only Full breakdown ↓
scored 2026-07-27 · rubric v0.5

1 APIs

CompanyArtificial IntelligenceOn-Device AIInferenceLLMSDKMachine LearningEdge AIApple SiliconText to Speech

Kin Score

Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5

Composite quality — 22.5/100 · emerging

Contract Quality 0.0 / 25

Developer Ergonomics 7.0 / 20

Commercial Clarity 6.8 / 20

Operational Transparency 0.7 / 13

Governance 0.0 / 12

Discoverability 8.0 / 10

Agent readiness — 0/100 · human only

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 15

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

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/mirai: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 1

Individual APIs this provider publishes, each with its own machine-readable definition.

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

SignUp

SignUp

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Build 1

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Access & Security 1

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Operate 1

Status, limits, changes, and where to get help

Support

Support

Commercial 2

Pricing, plans, and the legal terms of use

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 2

The organization behind the API

Website

Website

Blog

Blog

Source (apis.yml)

aid: mirai
name: Mirai
description: Mirai (trymirai.com) is an on-device AI infrastructure company building uzu, a high-performance, Rust-based inference
  engine that runs large language, text-to-speech, and classification models directly on consumer hardware — Apple Silicon,
  iOS, macOS, and beyond — with zero inference cost and full data privacy. The uzu SDK exposes a single high-level API across
  Python, Swift, TypeScript, and Rust, adding speculative decoding, structured output, and built-in performance metrics, plus
  an optional cloud path for hosted models. Founded by the co-creators of Reface and Prisma and backed by a $10M seed round
  led by Uncork Capital.
url: https://raw.githubusercontent.com/api-evangelist/mirai/refs/heads/main/apis.yml
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source: []
  generated: '2026-07-22'
  method: derived
image: https://trymirai.com/images/og/default.jpg
x-type: company
x-source: vc-portfolio
x-backed-by:
- uncork-capital
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-20'
tags:
- Company
- Artificial Intelligence
- On-Device AI
- Inference
- LLM
- SDK
- Machine Learning
- Edge AI
- Apple Silicon
- Text to Speech
apis:
- name: Mirai uzu Inference SDK
  description: uzu is Mirai's first-party, high-performance on-device inference engine. A single high-level API — shared across
    Python, Swift, TypeScript, and Rust — downloads and runs LLM, text-to-speech, and classification models locally, with
    speculative decoding, structured output, and an optional cloud path.
  humanURL: https://docs.trymirai.com
  tags:
  - On-Device AI
  - Inference
  - SDK
  properties:
  - type: Documentation
    url: https://docs.trymirai.com
  - type: GettingStarted
    url: https://docs.trymirai.com/quick-start/chat
  - type: Packages
    url: packages/mirai-packages.yml
  - type: SDKs
    url: packages/mirai-packages.yml
  - type: LLMsTxt
    url: llms/mirai-llms.txt
  - type: SourceCode
    url: https://github.com/trymirai/uzu
common:
- type: DomainSecurity
  url: security/mirai-domain-security.yml
- type: Website
  url: https://trymirai.com
- type: DeveloperPortal
  url: https://platform.trymirai.com
- type: Documentation
  url: https://docs.trymirai.com
- type: GettingStarted
  url: https://docs.trymirai.com/quick-start/chat
- type: SignUp
  url: https://platform.trymirai.com
- type: GitHubOrganization
  url: https://github.com/trymirai
- type: Blog
  url: https://trymirai.com/blog
- type: Support
  url: https://discord.com/invite/trymirai
- type: TermsOfService
  url: https://trymirai.com/terms-of-use
- type: PrivacyPolicy
  url: https://trymirai.com/privacy-policy
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 3
  pass: local-v1