# Kev

**Canonical:** https://apis.io/providers/kev/  
**APIs profiled:** 1

Kev is an open-source (Apache-2.0) family of small decision models built on Qwen3.5/Qwen3.8 by Jared Palmer, released on GitHub and Hugging Face. Its self-hosted server exposes an HTTP API that, per the README, "matches TypeSafe's System One" (POST /v1/systemone with noul, choice and score questions). Not a Cognition product. No OpenAPI or JSON Schema file is published in the repository.

## Kin Score — 4.7 / 100 (minimal)

Scored 2026-11-06 under rubric 0.27.0. Trend: flat (-1.0 from 5.7).

| Facet | Score |
|---|---|
| Discoverability | 53.6 |
| Contract Quality | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 5.3 |
| Developer Ergonomics | 4.8 |
| Access Clarity | 0.0 |

Regulatory layer — **Horizontal (data, software, accessibility, platform)**: 0.0 (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 |
| MCP Tool Quality | na |

## Access

Unknown — onboarding: unknown, pricing: unknown, trial: no (confidence: low).

## APIs (1)

- **Kev System One API (self-hosted)** — Self-hosted HTTP server (python -m kev.serve, default 127.0.0.1:8009). Documented paths in the README: POST /v1/systemone, GET /v1/models, POST /v1/systemone/permute, POST /v1/s...

## Tags

Company, Artificial Intelligence, Decision Models, Open Source, Self-Hosted

---

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