Features
28-language code graph with 6 cross-language bridges
57 core MCP agent tools for structural queries
227 total MCP tools including blast-radius analysis
Blast-radius check with production traffic weighting
AST-level clone detection with identifier rename confidence
Algorithmic risk review (O(n²), N+1, pattern-based)
Pre-change gates with BLOCK/REVIEW verdicts
Tamper-evident audit trail (in-toto v1) with HMAC-linked receipts
SARIF export for GitHub Code Scanning
Local execution with zero network egress and no API keys
241 CLI commands for exploration, health, security
MCP runtime security with egress redaction (v13.3)
4-mode MCP policy enforcement (read_only, safe_edit, migration, autonomous_pr)
PR Replay audit for retrospective analysis on up to 90 PRs
Governance evidence pack for SOC 2 / ISO 42001 mapping
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
