Home / Agent Debugging & Replay
Coval
Simulation-first testing and replay for voice/chat agents, borrowing evaluation methodology from autonomous-vehicle testing.
| Category | Agent Debugging & Replay |
| OpenTelemetry-native | Yes — no proprietary-SDK lock-in |
| Open source | No |
| Self-hostable | No |
| Pricing model | paid |
| Pricing notes | Contact pricing |
| Framework integrations | openai-sdk, vapi, retell, livekit |
| Funding / ownership | $3.3M seed (MaC Venture Capital, 2024) |
Pricing/feature source: https://www.coval.dev
Frequently asked questions
Is Coval open source?
No — Coval is a proprietary/commercial product.
Can I self-host Coval?
No — Coval is cloud-only; there is no self-hosted deployment.
Is Coval OpenTelemetry-native?
Yes — Coval speaks OpenTelemetry (OTLP) natively, so there is no proprietary-SDK lock-in.
How much does Coval cost?
Paid. Contact pricing