Features
Scalable load testing for HTTP, GraphQL, Socket.IO, WebSocket, and Playwright browser scenarios
Distributed load testing on AWS Lambda, AWS Fargate, and Azure Container Instances
Turbo Runner for automatic sharding and parallelization of Playwright test suites (up to 10x faster)
Synthetic monitoring with browser or API checks (checks UI coming soon)
Automatic Web Vitals tracking on all pages
GitHub Actions integration with PR comments and linked test reports
Centralized dashboard for all test results, traces, screenshots, and attachments
W3C Trace Context propagation for correlating backend traces with load tests (v2.0.31)
OpenTelemetry support for exporting metrics and traces (SDK 2.x)
Stash API for programmatic access to test artifacts and results
Slack, PagerDuty, and email alerts for test failures and performance regressions
Plugin ecosystem: Slack, expect, ensure, apdex, metrics-by-endpoint, fake-data, hls, fuzzer
VS Code Extension with context-aware autocomplete and inline documentation
Cost reporting for distributed test runs
CLI v2.0.31 with Playwright 1.59.1, Got v14.6.6, Fargate self-termination
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
