TypeSafe AI

TypeSafe AI is a San Francisco AI lab building System One models — a class of model trained to return typed, calibrated decisions for software instead of generated text. Its flagship and first System One model, Jev, is served by a single HTTP endpoint: POST /v1/systemone takes a `state` (a string, JSON object, or array) plus a map of typed questions and returns one structured answer per question. Three question primitives are published: Noul (a yes/no question answered with the probability the answer is yes), Choice (one option from a caller-defined set, returned with the full probability distribution) and Score (a rating against ordered rubric levels, returned as a probability-weighted value plus a legend). Choice and Score answers also carry a confidence value derived from the distribution, which is the mechanism TypeSafe intends callers to threshold on to decide when code may act autonomously and when it must escalate to a human. The model is trained with Reinforcement Learning for Calibrated Decisions (RLCD) rather than RLHF, is not fine-tuned or LoRA-adapted per customer, and is not trained on customer requests or responses. The company publishes an OpenAPI 3.1 contract on its API host, official Python and TypeScript SDKs, an installable Agent Skill for Claude Code and other coding agents, an A2A agent card, an anonymous documentation MCP server, an llms.txt index, a Better Stack status page and a Vanta trust center.

TypeSafe AI publishes 3 API contracts indexed on the APIs.io network, including Models API, Systemone API, and 1 more. Tagged areas include Artificial Intelligence, Machine Learning, Classification, Content Moderation, and Decision Support.

TypeSafe AI’s developer surface includes documentation, API reference, getting-started guide, signup flow, engineering blog, authentication, changelog, and 36 more developer resources.

🌐 Visit website 📡 Source on GitHub
52.1/100 developing ▬ flat Agent 38/100 agent ready Front door AI 5/6 prominent Full breakdown ↓
scored 2026-10-09 · rubric v0.23.0
4 published contracts 1 MCP Servers
Artificial IntelligenceMachine LearningClassificationContent ModerationDecision SupportStructured OutputsInferenceLLM AlternativeAgent SkillsMCPAgent-NativeDeveloper ToolsA2A

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-10-09 · rubric v0.23.0
Composite quality — 52.1/100 · developing
Contract Quality 9.1 / 19
Developer Ergonomics 10.4 / 15
Access Clarity 5.3 / 15
Operational Transparency 3.6 / 10
Contract Governance 1.6 / 9
Discoverability 6.1 / 8
Regulatory Posture 7.1 / 15
Create-or-Update Ergonomics 0.0 / 10
Agent readiness — 38/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 0 / 10
Documented Reversibility 0 / 6
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 7 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 5
Well-Known Catalog 4 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 8 / 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
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 applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.
The six quality facets above are damped to 75 points between them, because the conditional facet above carries the other 25. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 75% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.
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 github.com/api-evangelist/typesafe-ai: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Standards implemented 1

Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.

Agent Skills
tagged — the provider's own APIs.json carries the standard as a tag; implementation not verified

APIs 3

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

TypeSafe AI Documentation MCP Server

Hosted, anonymous, read-mostly MCP server over the published TypeSafe documentation corpus. Three tools: search_type_safe_ai (knowledge-base search), query_docs_filesystem_type_...

TypeSafe AI Models API

The Models API from TypeSafe AI — 1 operation(s) for models.

TypeSafe AI Systemone API

The Systemone API from TypeSafe AI — 1 operation(s) for systemone.

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

TypeSafe AI

TypeSafe runs a live, anonymous, hosted MCP server at https://docs.typesafe.ai/mcp. It answered a cold JSON-RPC tools/list with no credentials and returned three real tools with...

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Typesafe Ai Plans Pricing

0 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Typesafe Ai Rate Limits

0 limits

RATE LIMITS

OpenAPI Overlays 1

Overlays applied on top of this provider's contracts. Each card says who wrote it: a document the provider publishes, or one API Evangelist derived or generated.

Typesafe Ai Openapi Overlay

9 actions · servers · typesafe-ai-openapi.json

GENERATED

Security Posture 4

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

Typesafe Ai Authentication

http · 1 scheme

SECURITY

Typesafe Ai Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Typesafe Ai Vulnerability Disclosure

Hackerone · contact published

SECURITY

Typesafe Ai Trust Center

observed, observed_note, how_to_close

SECURITY

Resources

Get Started 5

Portal, sign-up, and the first successful call

DeveloperPortal
DeveloperPortal
 GettingStarted
GettingStarted
 SignUp
SignUp
 Login
Login
 Sandbox
Sandbox

Documentation 2

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

MCPServer
MCPServer
 AgentSkill
AgentSkill
 LLMsTxt
LLMsTxt
 WellKnown
WellKnown

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions
Conventions
 Conformance
Conformance
 ErrorCatalog
ErrorCatalog
 Lifecycle
Lifecycle
 DataModel
DataModel

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 Packages
Packages
 SDKs
SDKs
 Examples
Examples

Access & Security 7

Authentication, authorization, and security posture

VulnerabilityDisclosure
VulnerabilityDisclosure
 DomainSecurity
DomainSecurity
 TrustCenter
TrustCenter
 SecurityTxt
SecurityTxt
 Authentication
Authentication
 Security
Security
 TrustCenter
TrustCenter

Scroll for all 7

Operate 4

Status, limits, changes, and where to get help

StatusPage
StatusPage
 ChangeLog
ChangeLog
 RateLimits
RateLimits
 IncidentNotification
IncidentNotification

Commercial 3

Pricing, plans, and the legal terms of use

TermsOfService
TermsOfService
 PrivacyPolicy
PrivacyPolicy
 Plans
Plans

Company 3

The organization behind the API

Website
Website
 Blog
Blog
 Careers
Careers

Other 6

Properties that don't map to a standard resource type

Leadership
Leadership
 AgentCard
AgentCard
 Overlay
Overlay
 Subprocessors
Subprocessors
 DataResidency
DataResidency
 AITransparency
AITransparency

Source (apis.yml)

apis.yml Raw ↑ 
aid: typesafe-ai
name: TypeSafe AI
description: 'TypeSafe AI is a San Francisco AI lab building System One models — a class of model trained to return typed,
  calibrated decisions for software instead of generated text. Its flagship and first System One model, Jev, is served by
  a single HTTP endpoint: POST /v1/systemone takes a `state` (a string, JSON object, or array) plus a map of typed questions
  and returns one structured answer per question. Three question primitives are published: Noul (a yes/no question answered
  with the probability the answer is yes), Choice (one option from a caller-defined set, returned with the full probability
  distribution) and Score (a rating against ordered rubric levels, returned as a probability-weighted value plus a legend).
  Choice and Score answers also carry a confidence value derived from the distribution, which is the mechanism TypeSafe intends
  callers to threshold on to decide when code may act autonomously and when it must escalate to a human. The model is trained
  with Reinforcement Learning for Calibrated Decisions (RLCD) rather than RLHF, is not fine-tuned or LoRA-adapted per customer,
  and is not trained on customer requests or responses. The company publishes an OpenAPI 3.1 contract on its API host, official
  Python and TypeScript SDKs, an installable Agent Skill for Claude Code and other coding agents, an A2A agent card, an anonymous
  documentation MCP server, an llms.txt index, a Better Stack status page and a Vanta trust center.'
url: https://raw.githubusercontent.com/api-evangelist/typesafe-ai/refs/heads/main/apis.yml
image: https://framerusercontent.com/images/RtIGTDwO43jR4ZDilesXiR5znc.jpg
x-type: company
x-source: harvest:direct-request
specificationVersion: '0.20'
created: '2026-09-19'
modified: '2026-09-19'
tags:
- Artificial Intelligence
- Machine Learning
- Classification
- Content Moderation
- Decision Support
- Structured Outputs
- Inference
- LLM Alternative
- Agent Skills
- MCP
- Agent-Native
- Developer Tools
- A2A
tags_raw:
- artificial-intelligence
- machine-learning
- classification
- content-moderation
- decision-support
- structured-outputs
- inference
- llm-alternative
- agent-skills
- mcp
- agent-native
- developer-tools
- Machine Learning
- Machine-Learning
- A2A
apis:
- aid: typesafe-ai:docs-mcp
  name: TypeSafe AI Documentation MCP Server
  description: 'Hosted, anonymous, read-mostly MCP server over the published TypeSafe documentation corpus. Three tools: search_type_safe_ai
    (knowledge-base search), query_docs_filesystem_type_safe_ai (read-only rg/tree/head over a virtualised in-memory filesystem
    of the docs) and submit_feedback (the one write, reporting a documentation defect). It does NOT expose the System One
    evaluation endpoint — an agent can read everything about Jev over MCP and call none of it.'
  humanURL: https://docs.typesafe.ai/introduction
  baseURL: https://docs.typesafe.ai/mcp
  tags:
  - MCP
  - Agent-Native
  - Developer Tools
  tags_raw:
  - mcp
  - agent-native
  - developer-tools
  properties:
  - type: MCPServer
    url: mcp/typesafe-ai-mcp.yml
  - type: MCPServer
    name: MCP endpoint (provider-hosted)
    url: https://docs.typesafe.ai/mcp
  - type: ToolCrosswalk
    url: mcp/typesafe-ai-tool-crosswalk.yml
  - type: Documentation
    url: https://docs.typesafe.ai/agent-skill
- aid: typesafe-ai:typesafe-ai-models-api
  name: TypeSafe AI Models API
  description: The Models API from TypeSafe AI — 1 operation(s) for models.
  humanURL: https://docs.typesafe.ai/api
  baseURL: https://api.typesafe.ai
  tags:
  - Models
  properties:
  - type: OpenAPI
    url: openapi/typesafe-ai-models-api-openapi.yml
  - type: Documentation
    url: https://docs.typesafe.ai/introduction
  - type: APIReference
    url: https://docs.typesafe.ai/api
  - type: GettingStarted
    url: https://docs.typesafe.ai/introduction/quickstart
  - type: Authentication
    url: authentication/typesafe-ai-authentication.yml
  - type: Conventions
    url: conventions/typesafe-ai-conventions.yml
  - type: ErrorCatalog
    url: errors/typesafe-ai-problem-types.yml
  - type: DataModel
    url: data-model/typesafe-ai-data-model.yml
  - type: Examples
    url: examples/typesafe-ai-examples.yml
  - type: RateLimits
    url: rate-limits/typesafe-ai-rate-limits.yml
- aid: typesafe-ai:typesafe-ai-systemone-api
  name: TypeSafe AI Systemone API
  description: The Systemone API from TypeSafe AI — 1 operation(s) for systemone.
  humanURL: https://docs.typesafe.ai/api
  baseURL: https://api.typesafe.ai
  tags:
  - Systemone
  properties:
  - type: OpenAPI
    url: openapi/typesafe-ai-systemone-api-openapi.yml
  - type: Documentation
    url: https://docs.typesafe.ai/introduction
  - type: APIReference
    url: https://docs.typesafe.ai/api
  - type: GettingStarted
    url: https://docs.typesafe.ai/introduction/quickstart
  - type: Authentication
    url: authentication/typesafe-ai-authentication.yml
  - type: Conventions
    url: conventions/typesafe-ai-conventions.yml
  - type: ErrorCatalog
    url: errors/typesafe-ai-problem-types.yml
  - type: DataModel
    url: data-model/typesafe-ai-data-model.yml
  - type: Examples
    url: examples/typesafe-ai-examples.yml
  - type: RateLimits
    url: rate-limits/typesafe-ai-rate-limits.yml
common:
- type: VulnerabilityDisclosure
  url: security/typesafe-ai-vulnerability-disclosure.yml
- type: DomainSecurity
  url: security/typesafe-ai-domain-security.yml
- type: Website
  url: https://typesafe.ai/
- type: DeveloperPortal
  url: https://docs.typesafe.ai/
- type: Documentation
  url: https://docs.typesafe.ai/introduction
- type: APIReference
  url: https://docs.typesafe.ai/api
- type: GettingStarted
  url: https://docs.typesafe.ai/introduction/quickstart
- type: SignUp
  name: Console sign-up / sign-in (passwordless — Continue with Google or emailed code)
  url: https://console.typesafe.ai/
- type: Login
  url: https://console.typesafe.ai/login
- type: TermsOfService
  url: https://typesafe.ai/legal/terms
- type: PrivacyPolicy
  url: https://typesafe.ai/legal/privacy-policy
- type: GitHubOrganization
  url: https://github.com/typesafe-ai
- type: Blog
  url: https://typesafe.ai/blog/introducing-system-one-models-and-jev
- type: Leadership
  url: https://typesafe.ai/team
- type: StatusPage
  url: https://status.typesafe.ai/
- type: TrustCenter
  name: Trust center (provider-hosted, Vanta)
  url: https://trust.typesafe.ai/
- type: MCPServer
  url: mcp/typesafe-ai-mcp.yml
- type: AgentCard
  url: a2a/typesafe-ai-a2a.yml
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/typesafe-ai-llms.txt
- type: WellKnown
  url: well-known/typesafe-ai-well-known.yml
- type: SecurityTxt
  url: well-known/typesafe-ai-security.txt
- type: Packages
  url: packages/typesafe-ai-packages.yml
- type: SDKs
  url: packages/typesafe-ai-packages.yml
- type: Authentication
  url: authentication/typesafe-ai-authentication.yml
- type: Conventions
  url: conventions/typesafe-ai-conventions.yml
- type: Conformance
  url: conformance/typesafe-ai-conformance.yml
- type: ErrorCatalog
  url: errors/typesafe-ai-problem-types.yml
- type: Lifecycle
  url: lifecycle/typesafe-ai-lifecycle.yml
- type: ChangeLog
  url: changelog/typesafe-ai-changelog.yml
- type: Plans
  url: plans/typesafe-ai-plans-pricing.yml
- type: RateLimits
  url: rate-limits/typesafe-ai-rate-limits.yml
- type: Sandbox
  url: sandbox/typesafe-ai-sandbox.yml
- type: DataModel
  url: data-model/typesafe-ai-data-model.yml
- type: Examples
  url: examples/typesafe-ai-examples.yml
- type: Overlay
  url: overlays/typesafe-ai-openapi-overlay.yaml
- type: Careers
  url: https://jobs.ashbyhq.com/typesafe-ai
- type: Security
  url: security/typesafe-ai-vulnerability-disclosure.yml
- type: TrustCenter
  name: Trust center probe (artifact)
  url: security/typesafe-ai-trust-center.yml
- type: IncidentNotification
  name: 72-hour security-incident notification (DPA 5.2) — harvest record in regulatory/typesafe-ai-regulatory-posture.yml
  url: https://typesafe.ai/legal/data-processing
- type: Subprocessors
  name: Subprocessor list named by the DPA (Vanta trust center; table is JS-rendered)
  url: https://trust.typesafe.ai/subprocessors
- type: DataResidency
  name: Hosted in the United States (Privacy Policy, International Visitors)
  url: https://typesafe.ai/legal/privacy-policy
- type: AITransparency
  name: Per-version model limitations (jev-1.13 jaggedness)
  url: https://docs.typesafe.ai/model-jaggedness/jev-1.13
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
x-enrichment:
  date: '2026-09-19'
  status: enriched
  artifacts_added: 32
  pass: local-v3
x-coverage:
  state: covered
  reason: null
  detail: Fully covered. The machine-readable contract was found on the API host root (https://api.typesafe.ai/openapi.json,
    200, OpenAPI 3.1.0) after the docs host returned "Asset not found" for every spec path, and the provider additionally
    serves a conformant A2A agent card, a live anonymous MCP server, two published Agent Skills and an llms.txt.
  evidence:
  - url: https://api.typesafe.ai/openapi.json
    status: 200
  - url: https://docs.typesafe.ai/.well-known/agent-card.json
    status: 200
  - url: https://docs.typesafe.ai/mcp
    status: 200
  checked: '2026-09-19'
x-a2a:
  verified: true
  probed: '2026-09-26'
  url: https://docs.typesafe.ai/.well-known/agent-card.json
  grade: conformant
  protocol_version: '0.3'
  control: 404

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/typesafe-ai"
All providers 
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose 
curl "https://apis.io/api/v1/providers/typesafe-ai/operations?limit=25"
How their score was established 
curl "https://apis.io/api/v1/providers/typesafe-ai/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.