{
  "schema_version": "openagent.agent_resource_packet.v1",
  "id": "res_deepeval",
  "slug": "deepeval",
  "name": "DeepEval",
  "canonical_url": "https://www.openagent.bot/tools/deepeval",
  "category": "tools",
  "resource_type": "tool",
  "summary": "DeepEval is an MIT-licensed LLM evaluation framework that provides over 15 built-in metrics for testing RAG pipelines, agentic workflows, retrieval quality, hallucination detection, and conversation safety with Pytest integration for CI/CD.",
  "capabilities": [
    "tool",
    "evals",
    "testing",
    "automation",
    "workflow-orchestration",
    "tool-calling"
  ],
  "constraints": [
    "open-source",
    "self-hosted",
    "local-first"
  ],
  "scenarios": [
    "self-hosted-ai",
    "developer-workflow"
  ],
  "deployment_modes": [
    "self_hosted"
  ],
  "interfaces": [
    "repo",
    "docs"
  ],
  "integrations": [],
  "permission_surface": [
    "memory"
  ],
  "risk_level": "low",
  "source_confidence": "high",
  "recommended_workflows": [
    "Coding agent workflow",
    "Evaluation and observability",
    "Local or private AI stack",
    "Memory or RAG workflow"
  ],
  "avoid_when": [
    "Teams that need only production monitoring",
    "Users who want a single benchmark score without custom test cases"
  ],
  "primary_actions": [
    "Inspect repository",
    "Read setup docs",
    "Open Homepage"
  ],
  "evidence_urls": [
    "https://github.com/confident-ai/deepeval",
    "https://docs.confident-ai.com",
    "https://www.confident-ai.com"
  ],
  "last_verified_at": "2026-06-24",
  "machine_readable": {
    "json_url": "https://www.openagent.bot/tools/deepeval.json",
    "markdown_url": "https://www.openagent.bot/tools/deepeval.md",
    "agent_json_url": "https://www.openagent.bot/tools/deepeval.agent.json"
  }
}