Features
Method-level runtime traces with arguments, return values, SQL, and timing
Diff execution traces before vs. after code changes to detect behavior shifts
Auto-generate deterministic JUnit 5 replay tests from captured traces
MCP (Model Context Protocol) server for AI agent runtime context
Integrate with Testcontainers for replaying external API interactions
Instrument HTTP clients (RestTemplate, OpenFeign), JDBC, Kafka, and more
Support Spring Boot full-context integration tests with auto-stubbed boundaries
Generate one-click Postman collections from runtime traces
Run autonomous regression suites in CI/CD without token usage
Self-hosted Docker deployment for air-gapped environments
WebSocket, SOAP, and WebSocket tracing
PR review with runtime comparison (baseline main + PR diff)
Automatic PII masking before capture
Binary capture and compression for low overhead (0.5-5% CPU)
Local-first privacy (data stays in your infrastructure)
Trace agent executions step by step
Monitor real-time dashboards with cost tracking
Online LLM-as-judge evals for quality scoring
Automated insights with unsupervised topic clustering
SmithDB purpose-built for agent traces
Sub-second query performance across millions of traces
Full-text search with inverted index
JSON key-path filtering and trajectory queries
Self-host SmithDB inside your VPC
LangSmith Engine for autonomous issue detection and fixes
Deploy and scale agents with LangSmith Deployment
Sandboxes for safe agent-generated code execution
Fleet agents for no-code agent creation
Supports Python, TypeScript, Go, Java SDKs
