Langfuse vs LangSmith
Langfuse
langfuse.com
LangSmith
langchain.comSide by side
| Figure | Langfuse | LangSmith |
|---|---|---|
| Price from | $29/mo | $39/mo |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | Yes | — |
| Web | Yes | Yes |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 10 | 3 |
| Spec score · Prompting Tool | 9.3 (#1) | 9.3 (#2) |
| Spec score · Model Monitoring Software | 9.0 (#3) | 9.0 (#4) |
| Spec score · AI LLM Evaluation Tools | 9.1 (#4) | 9.1 (#5) |
| Spec score · Llm Developer Tools | 8.9 (#4) | 9.0 (#3) |
| Spec score · LLM Observability Tools | 9.0 (#4) | 9.0 (#5) |
| Spec score · Llm Monitoring | 8.9 (#5) | 8.9 (#6) |
| Spec score · AI Agent Observability Tools | 9.0 (#6) | 9.1 (#4) |
| Spec score · Prompt Engineering Tools | 9.0 (#5) | 9.1 (#4) |
| Spec score · AI LLM Observability Tools | 9.0 (#5) | 9.1 (#3) |
| Documentation | Documentation covers observability, prompt management, evaluation, metrics, APIs, SDKs, integrations, compatibility, deployment, and security with versioned self-hosting guides. | LangChain publishes reference documentation, integration guides, deployment instructions, a CLI guide and a REST API reference. |
| Evaluation | Evaluation features include LLM-as-a-judge, code evaluators, user feedback, manual labeling, datasets, and experiments. | Evaluation supports offline datasets, online production evaluations, human annotation queues and side-by-side experiment comparison. |
| Funding | Crunchbase lists one seed funding round with five investors, including Y Combinator, La Famiglia, and Lightspeed Venture Partners, but hides the total amount. | LangChain announced a $125 million Series B at a $1.25 billion valuation on October 20, 2025. |
| Headquarters | Berlin, Germany; San Francisco, United States | San Francisco, California, United States |
| Integrations | Langfuse lists more than 100 integrations spanning OpenTelemetry, Python and TypeScript, model providers, agent frameworks, gateways, and developer tools. | Documented integrations cover OpenAI, Anthropic, Bedrock, Gemini, Mistral, LiteLLM, OpenTelemetry, CrewAI, Vercel AI SDK, PydanticAI, AutoGen and many other frameworks and providers. |
| Observability | Hierarchical traces capture LLM calls, tool invocations, and retrieval steps, with filtering by user, session, cost, latency, and metadata. | Its observability features include agent tracing, cost tracking, online LLM-as-judge and code evaluations, trajectory monitoring, and webhook or PagerDuty alerts. |
| Rating on G2 | 4.5 out of 5 from 1 review | 4.4 out of 5 from 78 reviews. |
| Rating on Gartner Peer Insights | 4.6 out of 5 from 5 ratings | 4.4 out of 5 from 25 ratings. |
| SDKs | Official SDKs are Python v5 and JavaScript/TypeScript v6; other languages can use OpenTelemetry instrumentation. | Official SDK documentation is provided for Python, JavaScript/TypeScript, Go and Java. |
| Security | Langfuse reports annual SOC 2 Type II and ISO 27001 audits, external penetration tests, encryption, access controls, GDPR compliance, and a HIPAA-ready region. | LangSmith's trust center lists SOC 2 Type II, ISO 27001:2022, GDPR and HIPAA compliance. |
| Self-hosting | The OSS edition can be deployed with Docker Compose, Kubernetes Helm, or Terraform guides for AWS, GCP, and Azure, including offline or air-gapped installations. | Enterprise customers can run LangSmith self-hosted or hybrid on Kubernetes in AWS, Google Cloud or Azure. |
| Support | Hobby includes community support via GitHub, Core includes in-app support, Pro includes prioritized in-app support, and Enterprise includes support SLA and a named lead support engineer. | The Developer plan includes community support, and the Enterprise plan lists a support SLA. |
| System requirements | The Kubernetes deployment guide requires Kubernetes 1.28 or newer, Helm 3.17 or newer, ClickHouse 25.12 minimum, Postgres 16 recommended, and Redis 7.2 recommended. | Agent Server deployments require PostgreSQL and Redis; self-hosted installations may use customer-managed PostgreSQL and Redis. |
| What it does | Langfuse is an open-source AI engineering platform for tracing, prompt management, evaluations, metrics, and iterative improvement of LLM applications and agents. | LangSmith is LangChain's framework-agnostic platform for observing, evaluating and deploying AI agents. |
Plans
Langfuse
- HobbyFree
- HobbyFree
- Core$29 a month
- Core$29 a month
- Pro$199 a month
- Pro$199 a month
- Teams Add-on$300 a month
- Teams Add-on$300 a month
- Enterprise$2,499 a month
- Enterprise$2,499 a month
In their own words
Langfuse
Langfuse is an open-source AI engineering platform for teams debugging, analyzing, and iterating on AI agent applications. Its tracing records prompts, model responses, token use, latency, tool calls, retrieval steps, and metadata. Prompt Management stores, versions, deploys, and tests prompts, then links them to traces. Evaluation features include LLM-as-a-judge, code evaluators, user feedback, manual labeling, datasets, and experiments. Integrations include Python and JS/TS SDKs, OpenTelemetry, an API, CLI, MCP Server, and popular AI frameworks. Teams can self-host the MIT-licensed core on customer infrastructure using Docker, with options including Docker Compose, Kubernetes, AWS, and Azure. Langfuse reports annual SOC 2 Type 2 and ISO 27001 audits, external penetration tests, GDPR compliance, a DPA, and a HIPAA-ready region. Its Cloud traffic uses TLS 1.2+ and stored data uses AES-256 encryption. The free Hobby plan is free and includes 50k units per month, 30 days of data access, two users, and community support via GitHub. Core costs $29 a month, billed monthly.
LangSmith
LangSmith is a commercial agent-engineering platform for building, evaluating, deploying, monitoring, and improving AI agents. It supports offline evaluations on curated datasets and real-time scoring of production interactions. Evaluation methods include human review, heuristic checks, LLM-as-judge evaluators, pairwise comparisons, and custom Python or TypeScript evaluators. Annotation queues route runs to subject-matter experts for feedback that can calibrate evaluations, improve prompts, or augment datasets. The Playground compares prompt versions or model providers, and LangSmith chat can auto-improve prompts. Observability includes agent and retrieval tracing, token and general cost tracking, trajectory monitoring, online evaluations, and webhook or PagerDuty alerts. Traces can arrive through SDKs or an API from LangGraph, custom Python, or other stacks; SDKs are listed for Python, TypeScript, Go, and Java. Hosting ranges from cloud to hybrid and self-hosted Enterprise options. The Developer plan costs nothing, Plus costs $39 a month, and Enterprise pricing is custom.