# Ashr

**Canonical:** https://apis.io/providers/ashr/  
**Website:** https://ashr.io  
**APIs profiled:** 0

Ashr (Ashr Labs) is a testing and evaluation platform for AI agents. It lets teams test agents in real environments, generate realistic user-journey datasets, run graded evaluations across text, voice, image, and file modalities, catch regressions, and monitor agents in production. Ashr integrates as a Python or TypeScript SDK (pip install ashr-labs) into an existing codebase, exposing an AshrLabsClient plus EvalRunner and RunBuilder to fetch a dataset, run it against your agent, submit results for server-side grading, poll graded metrics, and trace production runs. The hosted Ashr Labs console at lab.ashr.io provides datasets, test timelines, prompt versioning, and analytics. Founded by Shreyas Kaps and Rohan Kulkarni; Y Combinator Winter 2026; based in San Francisco.

## Kin Score — 23.4 / 100 (emerging)

Scored 2026-08-17 under rubric 0.11.0. Trend: flat (+0.0 from 23.4).

| Facet | Score |
|---|---|
| Discoverability | 57.4 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Operational Transparency | 0.0 |
| Developer Ergonomics | 43.5 |
| Commercial Clarity | 44.7 |

## Agent readiness — 9.0 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| MCP Server | no |
| Auth Clarity | yes |
| 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 |

## Access

Self-serve signup — onboarding: self-serve, pricing: unknown, trial: no (confidence: medium).

## Security (2)

- **Ashr Authentication** — apiKey · 1 scheme
- **Ashr Domain Security** — TLSv1.3 · DMARC

## Tags

Company, AI Agents, Agent Testing, Evaluation, Observability, LLM, Developer Tools, SDK

---

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