client.tracer | Record traces: decorator, context manager, sessions, tool calls, span trees | Tracing |
agentx.integrations.* | One-line capture for LangChain/LangGraph, OpenAI Agents, CrewAI, AutoGen, ADK, LlamaIndex, Databricks/MLflow, Moveworks, and raw OpenAI/Anthropic clients | Integrations |
client.evaluations | Datasets, evaluator configs, runs: run(...).execute(fn).finalize() | Evaluations |
client.evaluations.prompts | The prompt registry: pull versioned prompts at runtime | Prompt Management |
client.monitor | Patterns, online evaluators, and per-agent profiles from code | Monitor |
client.outcomes / client.feedback | Report real-world outcomes and end-user votes for judge calibration | Outcomes |
report.gate() / run_eval() | CI pass/fail gates with rating floors and no-regression checks | CI/CD |
CLI: agentx-moveworks, agentx-databricks | Pull importers replaying external platforms’ activity as traces | Moveworks · Databricks |