Agent QA alternatives

Agent-driven runtime for testing web, Android, and iOS user flows from YAML, with a local dashboard, CLI/MCP control, and recorded evidence. Traction: Submitted via intake issue #182 Full Agent QA record →

  1. 1 Datadog Bits AI Use-case-specific agent harnesses

    also in Use-case-specific agent harnesses · also has MCP

    OSS ? Self-host — Managed ✓ MCP ✓ Compare with Agent QA →

  2. 2 Dynatrace Davis CoPilot (now Dynatrace Assist) Use-case-specific agent harnesses ⚠ renamed — now Dynatrace Assist

    also in Use-case-specific agent harnesses · also has MCP

    OSS ? Self-host ? Managed ? MCP ✓ Compare with Agent QA →

  3. 3 HubSpot Breeze AI Agents Use-case-specific agent harnesses

    also in Use-case-specific agent harnesses · also has MCP

    OSS ? Self-host ? Managed ? MCP ✓ Compare with Agent QA →

  4. 4 OpenAI Deep Research Use-case-specific agent harnesses

    also in Use-case-specific agent harnesses · also has MCP

    OSS ? Self-host ? Managed ? MCP ✓ Compare with Agent QA →

  5. 5 PagerDuty AIOps Use-case-specific agent harnesses

    also in Use-case-specific agent harnesses · also has MCP

    OSS ? Self-host ? Managed ? MCP ✓ Compare with Agent QA →

  6. 6 Perplexity Deep Research Use-case-specific agent harnesses

    also in Use-case-specific agent harnesses · also has MCP

    OSS ? Self-host ? Managed ? MCP ✓ Compare with Agent QA →

  7. 7 Salesforce Agentforce Use-case-specific agent harnesses

    also in Use-case-specific agent harnesses · also has MCP

    OSS ? Self-host ? Managed ? MCP ✓ Compare with Agent QA →

  8. 8 Vanta Use-case-specific agent harnesses

    also in Use-case-specific agent harnesses · also has MCP

    OSS ? Self-host — Managed ✓ MCP ✓ Compare with Agent QA →

Ranked by shared memory design (storage, retrieval, conflict handling, memory unit), same section and shared must-haves (open source, self-hosting, MCP), with adoption as a tie-breaker. ✓ confirmed · — no · ? not in the catalog yet. Want picks for your own requirements? Use the chooser. Checking a whole project? Check your stack.