LangWatch
Open-source LLMOps platform for observability, evaluation, and agent simulation.
LangWatch is profiled here as a Observability tool for engineering teams. Read about features, pricing, and how it compares to related options in the tools directory.
Description
Short Intro: LangWatch is an open-source LLMOps platform founded in 2023 by Manouk Draisma (CEO, ex-Lightspeed) and Rogerio Chaves (CTO, who built Booking.com's first AI agents), both of whom met during an Antler residency in Amsterdam. The company raised a €1M pre-seed round in February 2025 from Passion Capital, Volta Ventures, and Antler. In April 2026, LangWatch launched an open-source AI red-teaming tool designed to test agent vulnerabilities through systematic multi-turn adversarial interactions rather than single-prompt attacks.
Key Capabilities:
LLM observability and OpenTelemetry-native tracing with full conversation flow and bottleneck visibility
Agent simulation engine that runs thousands of synthetic conversations across scenarios, languages, and edge cases before deployment
Prompt and model management with version control, feature-flag-style rollouts, and complete audit trails
Open-source red-teaming tool for testing AI agents against multi-turn adversarial attacks
DSPy-based optimizer integration for automated prompt improvement
Real-time evaluations with hallucination detection, jailbreak detection, and PII leak monitoring
LangWatch Skills for AI coding agents including Claude Code, enabling 2-minute instrumentation via a paste-in prompt
Non-technical PM and domain expert collaboration workflows built into the platform
Alternative tools
- HoneyHive
Evaluation and observability platform for AI agents
- Sentry
Error tracking and performance monitoring for developers
- SigNoz
Open-source, OpenTelemetry-native observability platform
- Datadog
Unified observability for metrics, traces, and logs
- Arize AX
Enterprise platform for AI observability and evaluation
- OpenTelemetry
Vendor-neutral standard for traces, metrics, and logs