spb/tools-spboucher-ai

1{2  "slug": "langsmith",3  "name": "LangSmith",4  "aliases": ["smith.langchain.com", "LangSmith Deployment", "LangGraph Platform (former name of the deployment product)"],5  "vendor": { "name": "LangChain, Inc.", "slug": "langchain-inc", "website": "https://www.langchain.com" },6  "homepage_url": "https://www.langchain.com/langsmith/observability",7  "docs_url": "https://docs.langchain.com/langsmith/observability",8  "pricing_url": "https://www.langchain.com/pricing",9  "product_type": "platform",10  "product_status": "active",11  "summary": "LangChain's hosted platform for tracing, evaluating and deploying LLM applications and agents, with prompt tooling, an LLM gateway and cloud, hybrid or self-hosted options",12  "description": "LangSmith is the commercial platform from LangChain, Inc. for operating LLM applications. Its observability layer records traces of what agents did, groups them into threads, supports dashboards, alerts and feedback collection, and builds datasets from production runs. Evaluation covers offline experiments and online evaluators, annotation queues and automation rules, and the Prompt Hub and Playground handle prompt engineering. Newer components include Deployment (hosting LangGraph agents with scheduling, MCP exposure and an Assistants API; formerly LangGraph Platform), Engine (automated detection and diagnosis of recurring trace problems), Fleet (no-code agents), Sandboxes for agent-generated code and an LLM Gateway with cost controls and redaction that traces calls without SDK changes.\n\nTracing works with LangChain and LangGraph through environment variables but is not limited to them; OpenAI, Anthropic, CrewAI, Vercel AI SDK and Pydantic AI integrations are documented. Plans are Developer (free, single seat), Plus and Enterprise; cloud hosting is in US or EU regions, with hybrid (SaaS control plane, self-hosted data plane) and fully self-hosted deployments reserved for Enterprise. The platform is proprietary, so teams that need a free self-hosted tracing store usually compare it with Langfuse.",13  "capabilities": ["Tracing with threads, dashboards, alerts and feedback", "Offline and online evaluation, annotation queues and automation rules", "Prompt Hub and Playground", "Deployment of LangGraph agents with cron, MCP and Assistants API", "Engine for automated trace-issue diagnosis", "LLM Gateway with cost controls, fallbacks and PII redaction", "Cloud (US/EU), hybrid and self-hosted deployment on Enterprise"],14  "workflows": ["Trace a LangGraph agent during development with one environment variable", "Turn production failures into an evaluation dataset", "Deploy an agent as a managed endpoint with scheduled runs"],15  "advantages": ["Tightest integration with LangChain and LangGraph", "Observability, evals, prompts and deployment in one product", "Free Developer tier"],16  "limitations": ["Proprietary; self-hosting only on Enterprise", "Usage metered by traces and platform units", "Product renames (LangGraph Platform to LangSmith Deployment) date older docs"],17  "prerequisites": ["LangSmith account and API key", "Application instrumented via LangChain, an SDK or the gateway"],18  "audiences": ["Teams building on LangChain and LangGraph", "Organizations wanting a managed agent-hosting and observability stack"],19  "alternatives": ["langfuse", "braintrust", "weights-and-biases", "promptfoo"],20  "categories": [{ "slug": "llm-ops", "primary": true }],21  "tags": ["llm", "monitoring", "evaluation", "agents", "prompt-management"],22  "use_cases": ["evaluate-llm-apps", "monitor-services", "build-agents"],23  "operating_systems": ["web"],24  "execution_modes": ["cloud", "self-hosted"],25  "interfaces": ["web", "api", "sdk"],26  "deployment_models": ["saas", "hybrid", "on-premises"],27  "integrations": ["LangChain", "LangGraph", "OpenAI", "Anthropic", "CrewAI", "Vercel AI SDK", "Pydantic AI", "OpenTelemetry"],28  "data_formats": ["JSON"],29  "languages": ["Python", "TypeScript"],30  "source_model": "proprietary",31  "pricing_model": ["freemium", "paid", "enterprise"],32  "pricing_checked_at": "2026-11-02",33  "self_hostable": true,34  "sources": [35    { "url": "https://www.langchain.com/langsmith/observability", "type": "official_site", "title": "LangSmith Observability", "supports": ["name", "summary"], "checked_at": "2026-11-02" },36    { "url": "https://docs.langchain.com/langsmith/observability", "type": "official_docs", "title": "LangSmith documentation", "supports": ["capabilities", "integrations", "deployment_models"], "checked_at": "2026-11-02" },37    { "url": "https://www.langchain.com/pricing", "type": "pricing_page", "supports": ["pricing_model", "deployment_models"], "checked_at": "2026-11-02", "note": "Developer, Plus, Enterprise; cloud US/EU, hybrid and self-hosted" }38  ],39  "confidence": "high",40  "discovery_method": "editorial-research",41  "depth": "standard",42  "editorial_status": "reviewed",43  "visibility": "public",44  "featured": false,45  "author": "batch-A"46}47