Features
Live timeline of prompts, tool calls, skill invocations, and token consumption
Real-time context window breakdown (system, tools, memory, skills, messages tokens)
Session throughput pulse visualization
Skills & MCP server inventory with last-used timestamps
Claude Radio background audio (curated stations + custom YouTube URLs)
Per-tab working directory and git branch tracking
Account-global usage rate-limit windows
Session correlation by process (survives upstream changes)
What's New notes after updates
Auto-update via signed sidecar binary
One-click upgrade to Premium via Polar checkout
Support for new Claude model families in Context/Usage capture
Filter for 'waiting for input' nudges
Timeline Build chip persistence
Resolved live stream at startup
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
