ClawMetry
Netherlands
See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons. ...
Agent observability and evaluation tools record, trace and test what LLM applications and agents do, so teams can debug failures, measure quality and monitor cost.
The leading AI agent observability and evaluation tools on botshub include ClawMetry, Opik and OrcaReplay. botshub lists 10 reviewed AI agent observability and evaluation tools from companies around the world.
See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons. ...
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
OrcaReplay β Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.
Trace, evaluate, and improve AI agents with one open platform. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.
AI Observability & Evaluation
Instill trust in your agent evals
Every Agent Needs AgentOps.
AI Gateway & LLM Observability
LangSmith provides tools for debugging, testing, evaluating, and monitoring LLM applications, integrating seamlessly with LangChain for comprehensive AI agent observability
πΉοΈ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.
| # | Name | Maker | Based in | Type | Open source |
|---|---|---|---|---|---|
| 1 | ClawMetry | ClawMetry | Netherlands | β | Yes |
| 2 | Opik | Opik | β | β | Yes |
| 3 | OrcaReplay | OrcaReplay | United States | β | Yes |
| 4 | LangFuse | LangFuse | Germany | β | Yes |
| 5 | Arize Phoenix | Arize Phoenix | β | β | Yes |
| 6 | Kitaru | Kitaru | Germany | β | Yes |
| 7 | AgentOps | AgentOps | United States | β | Yes |
| 8 | Helicone | Helicone | United States | β | Yes |
| 9 | LangSmith | LangChain | United States | β | Yes |
| 10 | Pezzo | Pezzo | United States | β | Yes |
Netherlands
See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons. ...
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
United States
OrcaReplay β Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.
Germany
Trace, evaluate, and improve AI agents with one open platform. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.
AI Observability & Evaluation
LangSmith provides tools for debugging, testing, evaluating, and monitoring LLM applications, integrating seamlessly with LangChain for comprehensive AI agent observability
United States
πΉοΈ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.