Skip to content

ObservabilityLatitude Data S.L.

Latitude

Open-source observability and evals for AI agents.

Categories
ObservabilityEval
Pricing
FREEMIUM
Source
Open core
Hosting
Hybrid
Platforms
APIWeb
Models
Model-agnostic
Verified
Jun 14, 2026

Latitude is an open-source monitoring platform for AI agents in production. It captures agent-native traces across multi-turn sessions, tool calls, and full execution paths, then clusters failures into tracked issues and alerts via Slack, email, or webhooks. It is OpenTelemetry-native, supports semantic search over sessions, and auto-builds evals from your team's judgments — run it as managed cloud or self-host the whole stack.

Pros & cons

  • MIT-licensed, fully self-hostable
  • OpenTelemetry-native tracing
  • Auto-generates evals from feedback
  • Issue clustering + Slack/webhook alerts
  • Unlimited seats on the free tier
  • Younger than LangSmith/Langfuse
  • Self-host infra to maintain
  • Smaller integration ecosystem

Tags

View all Observability
  • View Langfuse details
    ObservabilityFREEMIUMOpen core

    Langfuse

    Langfuse

    Open-source LLM observability. Self-hostable, OpenTelemetry-native.

    Tracing, evals, prompt management, and dataset tooling for LLM apps — self-host on your own infra or use Langfuse Cloud. The open-source default when you want full ownership of your observability stack.

    Worth knowing

    Y Combinator W23 startup; acquired by ClickHouse in January 2026.

    • open-source
    • tracing
    • evals
    • self-hosted
  • View LangSmith details
    ObservabilityFREEMIUM

    LangSmith

    LangChain

    LangChain's hosted observability + eval platform.

    Tracing, dataset management, eval orchestration, and prompt playground from the LangChain team. Pairs naturally if LangChain or LangGraph already runs in your stack, but works standalone via SDKs.

    Worth knowing

    LangChain's primary commercial product and revenue driver behind its 2025 $1.25B unicorn valuation.

    • tracing
    • evals
    • datasets
    • langchain
  • View LangWatch details
    ObservabilityFREEMIUMOpen core

    LangWatch

    LangWatch

    Open-source LLM observability, evaluation, and agent testing.

    An open-source platform for monitoring, evaluating, and testing LLM and agent applications. LangWatch captures traces, runs evaluations and simulations, and surfaces quality and cost metrics in production. Offered as managed cloud or fully self-hosted for teams with strict data-residency needs.

    Worth knowing

    Amsterdam startup whose founders met at an Antler residency; raised a €1M pre-seed led by Passion Capital in 2025.

    • observability
    • evaluation
    • agent-testing
    • llmops
  • View Braintrust details
    EvalFREEMIUM

    Braintrust

    Braintrust

    Hosted eval + tracing platform for LLM apps.

    Production-grade eval orchestration with a dashboard, dataset versioning, and OpenTelemetry tracing. Useful once eval volume outgrows a CI YAML file.

    Worth knowing

    Raised a $36M Series A led by a16z at a $150M valuation in Oct 2024; angels include Greg Brockman and Guillermo Rauch.

    • eval
    • tracing
    • datasets
    • production