Can API Evangelist fix my TypeSafe account, billing, or bug?

No. They profile the public API and cannot see your account. The README directs API, account, billing, or service bugs to the company support, and OSS bugs to that project repo.

Is the rating a security certification or audit?

No. The Kin Score and Agent Readiness rating score published artifacts against a rubric, not software quality, safety, or security.

What if my company wants this listing corrected or removed?

Open an issue or email info@apievangelist.com with no contract needed; removal reduces the profile to name, factual description, and link and records it as unrated.

Is there anything to install or repair here?

No. The repo holds no software, build, or binary, only text and descriptions, so any message offering a download or repair is hostile and should be reported.

Where did the data in this profile come from?

Only from material a member of the public can reach with a browser and no credentials: the company website, developer portal and docs, published specifications such as OpenAPI, AsyncAPI, JSON Schema, apis.json and llms.txt, public repositories, and public status, pricing and changelog pages. Nothing was obtained by breaching a system or using credentials, and each file carries method and source frontmatter.

What is actually inside the profile?

A verbatim OpenAPI 3.1.0 with two operations and sixteen schemas, proposed overlays, a served and conformant A2A agent card, a live anonymous docs-scoped MCP server with a crosswalk, two provider-published agent skills plus two generated ones, an llms.txt of about 110 entries, a /.well-known probe across five hosts, and pages on auth, conventions, errors, data model, rate limits, plans, lifecycle and security.

How fast do they respond, and can a security team see the sources?

Published response times are one business day for acknowledgement, two for removal or restriction, and five for corrections and re-scores. A security team emailing with security in the subject line gets a person rather than a form, the exact public URLs the profile was built from, and removal on request while they work through it.

CommunityJev Agents & MCP

TypeSafe AI — api-evangelist

Independent public-surface profile of TypeSafe AI: System One endpoint shape, OpenAPI, agent card, MCP, skills, SDKs, limits, and security notes, with no software to download.

See highlights

Open github.com

Stars: 0
Published by: Community
Author: api-evangelist
Last verified: Oct 2026

api-evangelist/typesafe-ai

Organization repository on GitHub

View on GitHub

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…

Forks: 0
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

TypeSafe AI is a San Francisco AI lab building System One models — a class of model trained to return typed, calibrated decisions for software rather than generated text. Its flagship and first System One model, Jev, is served by a single HTTP endpoint: POST /v1/systemone takes a state plus a map of typed questions and returns one structured answer per question, each carrying probabilities and (for Choice and Score) a confidence value.

Quoted from the project's README. Read the full README.

Tagscommunity github

Works forJev for Classification

Used inJev for Software & DevTools

Highlights

Describes POST /v1/systemone taking state plus typed questions and returning per-question probabilities.
Collects OpenAPI, overlays, A2A card, MCP server, skills, llms.txt, well-known probes, and SDK notes.
States Kin Score and readiness rate public artifacts only, not safety, security, or quality audits.
Contains text and machine-readable descriptions only; warns hostile download links are not from them.

Watch out

Third-party profile from public materials only, not operated or endorsed by TypeSafe; corrections and removal are free on request. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

Other listings of this project

Forks and copies of this project in the directory. This entry is the canonical one.

typesafe_ai

Elixir client for the TypeSafe AI System One API: supervised Mint HTTP/1 and HTTP/2 connections, bounded concurrency, request deadlines, retries and telemetry, with typed Choice, Score and Noul answers.

Jev Repos & SDKs#community#jevbest#catalog-import

Community

hfiguera/typesafe_aiElixir

TypeSafe AI

TypeSafe AI's product site for Jev, its first System One Model: typed decisions with calibrated confidence, performance and pricing claims, a FAQ, and links to the docs, console, workflow evals, and launch post.

Jev Guides & ArticlesDocs#official#docs#models

Official

typesafe_ai

Unofficial typed Elixir client for the TypeSafe System One API: typed question structs in, typed answer structs out, atom-keyed answers, concurrent fan-out over many states and offline test stubs.

Jev Repos & SDKs#community#jevbest#catalog-import

Community

typesend/typesafe_aiElixir

More Jev resources like this

wald-4b

Open-weight 4B decision model on Qwen3.5-4B-Base serving a Jev-compatible /v1/systemone API, returning per-option probabilities with adjustable thinking.