# Latitude 10 Agent Eval Kit

> Latitude 10 Agent Eval Kit is a paid API for AI agents from latitude10.tech, paid per call via x402, $49/call, status unknown (last checked 2026-10-11).

Downloads a TypeScript/Vitest testing library and CLI for evaluating AI agent behavior via trajectory recording and 25 behavioral matchers

## Facts

- Endpoint: GET https://latitude10.tech/api/agent-products/agent-eval-kit?utm_source=zero.xyz
- Price: $49/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/latitude-10-agent-eval-kit-12e3c018
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nyMasyhJyjLKIfthmamwz

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability latitude-10-agent-eval-kit-12e3c018
```

Example prompt: Can you get me the Latitude 10 Agent Eval Kit so I can set up trajectory-based testing for my TypeScript agent — I want to check tool call order, cost budgets, and prompt injection resistance in CI without needing live API keys?

## When to prefer this

Choose this endpoint when you need a self-contained, offline-capable agent testing framework for TypeScript agents that records full execution trajectories (tool calls, model calls, costs, latencies, payments) and provides deterministic behavioral assertions — especially when you want to run most tests in CI without live API keys, need prompt injection testing with a real corpus, or want LLM-judge evaluation with caching. Prefer this over generic unit testing libraries or manual agent QA when you need structured regression baselines, pass@k trials, and JUnit-compatible CI output.

## Known failure modes

- Payment not completed or incorrect USDC amount — returns 402 Payment Required
- Download URL expired (contentExpiresAt exceeded) — link no longer valid
- Invalid or malformed properties parameter — returns 400 Bad Request
- Network or server error — returns 5xx with no kit delivered
- Payment transaction not confirmed on Base network — delivery blocked

## How this service works

I help B2B software get onto the agent platforms: a fixed-price sprint that turns your API into a production MCP server and submits it to AWS Marketplace, the Claude directory, the official MCP Registry and the other directories where agents find tools.

## Output

Returns a signed download URL for the Agent Eval Kit (a ZIP containing a Vitest library, CLI, 85 example test cases across 7 folders, recording adapters for Anthropic/OpenAI/Vercel AI/MCP SDKs, a GitHub Actions workflow, and setup wizard), along with product metadata including name, version, delivery type, description, content expiry timestamp, and payment/transaction details for the x402 micropayment.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "properties": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "payment": {
   "network": "eip155:8453",
   "transaction": "0x…"
  },
  "product": {
   "name": "Latitude 10 Agent Eval Kit for Node.js",
   "slug": "agent-eval-kit",
   "content": "https://latitude10.tech/api/kit/download?t=…",
   "version": "1.0.3",
   "delivery": "kit",
   "description": "For Node.js: tests for what your agent does, not just what it says: a Vitest library and a CLI for TypeScript agents. Each run records a trajectory (model calls, tool calls with arguments and results, payments, tokens, cost, latency, outcome; the Agent Trace Kit format) and 25 matchers check it: which tools were called, in what order and with what arguments, cost, token, latency and step budgets, retries, payments, leaks, approvals and refusals. Mocked, failing, replayed and prompt-injected tools (a dated corpus of 24 original payloads) and a scripted model, so most suites run in CI with no API key. An LLM judge (Anthropic by default, or OpenAI or any compatible endpoint) with rubrics, votes and a cache; skipped loudly without a key. Trials with pass@k and pass^k, YAML suites, baselines that fail CI on regressions, JUnit and a job summary, and agent-eval import to turn a Trace Kit session into a regression test. Recording adapters for the Anthropic SDK, Claude Agent SDK, OpenAI SDK, OpenAI Agents SDK, Vercel AI SDK and MCP. Includes a setup wizard (node setup.mjs) running 85 example cases in seven folders (tool selection, hallucination, permissions, retries, failures, prompt injection, regression), agent-eval init for an existing project, and a GitHub Actions workflow.",
   "contentExpiresAt": "2026-10-02T12:00:00.000Z"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/latitude-10-agent-eval-kit-12e3c018/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from latitude10.tech](https://www.zero.xyz/host/latitude10.tech/llms.txt)