# LangWatch

**Canonical:** https://apis.io/providers/langwatch/  
**Website:** https://langwatch.ai  
**APIs profiled:** 28

LangWatch is an open-source LLM observability, evaluation, and AI agent testing platform. Built around OpenTelemetry-native tracing, LangWatch lets teams instrument LLM applications (LangChain, LangGraph, DSPy, OpenAI Agents, LiteLLM, Pydantic AI, CrewAI, AWS Bedrock, and more), run real-time and batch evaluations, version and deploy prompts, simulate multi-turn agent conversations against scripted scenarios and Judge Agents, manage labeled datasets, and govern model traffic through a virtual-key AI Gateway with budgets and semantic caching. The platform exposes a REST API at app.langwatch.ai, ships Python and TypeScript SDKs plus an MCP server, publishes the companion `scenario` agent-testing framework and `better-agents` standards, and runs on Apache-2.0 core (with `ee/` enterprise modules under commercial license) — deployable as LangWatch Cloud or self-hosted via Docker Compose, Helm, Kind, or full Kubernetes.

## Kin Score — 47.6 / 100 (developing)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 47.6).

| Facet | Score |
|---|---|
| Discoverability | 59.3 |
| Contract Quality | 60.9 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 44.7 |
| Developer Ergonomics | 42.9 |
| Commercial Clarity | 60.5 |
| Access Clarity | 60.5 |

## Agent readiness — 48.6 (agent-native)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| Reversibility Documented | documented |
| MCP Server | no |
| Auth Clarity | yes |
| Idempotency | verified |
| Error Semantics | verified |
| OpenAPI Examples | partial |
| Rate Limit Signal | documented |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Freemium · Self-serve signup — onboarding: self-serve, pricing: freemium, trial: no (confidence: high).

## APIs (28)

- **LangWatch Agents API** — The Agents API from LangWatch — 2 operation(s) for agents.
- **LangWatch Analytics API** — The Analytics API from LangWatch — 1 operation(s) for analytics.
- **LangWatch Annotations API** — The Annotations API from LangWatch — 3 operation(s) for annotations.
- **LangWatch Api Keys API** — The Api Keys API from LangWatch — 2 operation(s) for api keys.
- **LangWatch Budgets API** — The Budgets API from LangWatch — 2 operation(s) for budgets.
- **LangWatch Cache Rules API** — The Cache Rules API from LangWatch — 2 operation(s) for cache rules.
- **LangWatch Dashboards API** — The Dashboards API from LangWatch — 3 operation(s) for dashboards.
- **LangWatch Dataset API** — The Dataset API from LangWatch — 7 operation(s) for dataset.
- **LangWatch Evaluations V3 API** — The Evaluations V3 API from LangWatch — 2 operation(s) for evaluations v3.
- **LangWatch Evaluators API** — The Evaluators API from LangWatch — 3 operation(s) for evaluators.
- **LangWatch Graphs API** — The Graphs API from LangWatch — 2 operation(s) for graphs.
- **LangWatch LangWatch API API** — The LangWatch API API from LangWatch — 1 operation(s) for langwatch api.
- **LangWatch Model Defaults API** — The Model Defaults API from LangWatch — 2 operation(s) for model defaults.
- **LangWatch Model Providers API** — The Model Providers API from LangWatch — 2 operation(s) for model providers.
- **LangWatch Monitors API** — The Monitors API from LangWatch — 3 operation(s) for monitors.
- **LangWatch Projects API** — The Projects API from LangWatch — 2 operation(s) for projects.
- **LangWatch Prompts API** — The Prompts API from LangWatch — 8 operation(s) for prompts.
- **LangWatch Providers API** — The Providers API from LangWatch — 2 operation(s) for providers.
- **LangWatch Scenario Events API** — The Scenario Events API from LangWatch — 1 operation(s) for scenario events.
- **LangWatch Scenarios API** — The Scenarios API from LangWatch — 2 operation(s) for scenarios.
- **LangWatch Secrets API** — The Secrets API from LangWatch — 2 operation(s) for secrets.
- **LangWatch Simulation Runs API** — The Simulation Runs API from LangWatch — 3 operation(s) for simulation runs.
- **LangWatch Suites API** — The Suites API from LangWatch — 4 operation(s) for suites.
- **LangWatch Trace API** — The Trace API from LangWatch — 3 operation(s) for trace.
- **LangWatch Traces API** — The Traces API from LangWatch — 3 operation(s) for traces.
- **LangWatch Triggers API** — The Triggers API from LangWatch — 2 operation(s) for triggers.
- **LangWatch Virtual Keys API** — The Virtual Keys API from LangWatch — 4 operation(s) for virtual keys.
- **LangWatch Workflows API** — The Workflows API from LangWatch — 2 operation(s) for workflows.

## Agentic access (1)

- **Langwatch Agentic Access** — 133 operations · 85 acting · 3 human-in-the-loop

## Security (3)

- **Langwatch Authentication** — apiKey/http · 2 schemes
- **Langwatch Domain Security** — TLSv1.3 · HSTS · DMARC
- **Langwatch Trust Center** — ISO 27001, GDPR

## Plans (1)

- **Langwatch Plans Pricing**

## Tags

Artificial Intelligence, LLM, LLM Observability, LLM Evaluation, Agent Testing, Agent Simulation, Prompt Management, Datasets, Tracing, OpenTelemetry, AI Gateway, DSPy, LangChain, Open-Source, MCP, FinOps

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/langwatch/). Scores are computed from the provider's own public artifacts under a published rubric.