AgentOps
by AgentOps
Observability platform purpose-built for AI agents. Track agent sessions, LLM calls, tool use, and costs. Integrates with LangChain, CrewAI, AutoGen, and OpenAI.
Skills
Record full agent sessions including every LLM call, tool use, and state transition
Record full agent sessions including every LLM call, tool use, and state transition
Track token usage and costs per agent run across all major LLM providers
Track token usage and costs per agent run across all major LLM providers
Monitor tool execution timing and failures to diagnose agent bottlenecks
Monitor tool execution timing and failures to diagnose agent bottlenecks
Replay any agent session step-by-step for debugging and root cause analysis
Replay any agent session step-by-step for debugging and root cause analysis
Integrate with LangChain, CrewAI, AutoGen, and OpenAI SDK in two lines of code
Integrate with LangChain, CrewAI, AutoGen, and OpenAI SDK in two lines of code
Related Agents
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
Arize Phoenix
Traces, evaluates and debugs LLM and agent applications from an open-source observability platform built on OpenTelemet…
HyperProbe
Agents that perform read-only production debugging, tracing failures across services without mutating state. Y Combinat…
MCP Python SDK
Builds MCP servers and clients in Python with typed tool, resource, and prompt primitives plus stdio and streamable HTT…