Skip to main content
LLM observability · tools · 14 picks

Best LLM observability tools

Observability and tracing platforms for LLM and agent applications — traces, metrics, prompts, and evaluation.

Curated by @heyclaude-editors Updated 2026-06-19

Observability and tracing platforms for LLM and agent applications — traces, metrics, prompts, and evaluation.

Compared at a glance

The top 5 picks side by side on trust, install, platform support, and disclosed notes — full rationale for each below.

FieldLangSmith

Observability, evaluation, tracing, and testing platform for LLM applications and agent workflows.

Open dossier
Evidently

Open-source ML and LLM observability framework for evaluating, testing, and monitoring data quality, drift, model behavior, and AI application outputs.

Open dossier
Arize Phoenix

Open-source observability and evaluation tooling for LLM applications, traces, datasets, and experiments.

Open dossier
AgentOps

Open-source observability platform and SDK for tracing, debugging, replaying, and cost-monitoring AI agent and LLM application runs.

Open dossier
DeepEval

Open-source Python framework for unit-testing LLM applications, agents, RAG pipelines, metrics, regression suites, and traces.

Open dossier
Trust
Install riskReview firstReview firstReview firstReview firstReview first
Notes Safety · Privacy Safety Privacy Safety · Privacy · Safety Privacy Safety Privacy
Categorytoolstoolstoolstoolstools
Sourcesource-backedsource-backedsource-backedsource-backedsource-backed
AuthorLangChainEvidently AIArize AIAgentOpsConfident AI
Added2026-04-272026-06-032026-04-272026-06-032026-06-03
Platforms
CLI
CLI
CLI
CLI
CLI
Source repo
Safety notes— missingEvidently metrics and tests are decision support, not proof that a model, dataset, prompt, or LLM application is correct, fair, safe, or production-ready. Drift, data quality, and LLM judge results can be noisy or context-dependent, so thresholds should be calibrated on representative data before blocking releases or triggering alerts. Reports, test suites, and dashboards can influence deployment and incident workflows, so review generated conditions before wiring them into CI, monitoring, or agent-managed remediation. Synthetic data generation, prompt optimization, LLM-as-judge evaluations, and provider-backed metrics can call configured model services and should be scoped for cost and data handling. Self-hosted dashboards, local reports, and exported artifacts need normal access controls because they can become a shared source of operational decisions.— missingAgentOps instruments LLM calls, tools, operations, and agent workflows, so enable it intentionally in environments where captured traces are allowed. Cost and latency dashboards are useful for operations, but alerting and budget decisions still need human-reviewed thresholds. Self-hosted deployments require normal backend hardening for database access, secrets, authentication, and retained trace data.DeepEval metrics should be treated as regression and review signals, not proof that an LLM application is safe, correct, or production-ready. LLM-as-a-judge metrics can call configured model providers, consume quota, hit rate limits, and produce judge-model errors that need separate handling. Evaluation thresholds should be calibrated on real examples before they block deployments or trigger automated rollback, ranking, billing, or moderation decisions. Tracing instrumentation can wrap live application code, agents, retrievers, tools, and model calls; keep eval and production environments clearly separated.
Privacy notesLangSmith receives traces of your LLM and agent runs — prompts, outputs, tool calls, and metadata — sent to LangSmith's cloud (or your self-hosted instance); review what trace data leaves your environment and keep secrets out of logged inputs.Evidently can process dataset columns, feature values, predictions, labels, model metadata, prompts, retrieved context, responses, traces, evaluation scores, and custom metric outputs. HTML, JSON, and Python dictionary reports can contain samples, column names, feature distributions, prompt text, generated answers, labels, or other sensitive operational data. Evidently Platform and Cloud workflows add hosted storage, dashboards, dataset management, tracing, user management, and alerting that should be reviewed against team data-retention and access-control policies. LLM-based evaluations may send prompts, responses, references, or scoring context to configured model providers unless a local evaluation path is used. Local report files and dashboard exports should be kept out of public repositories and shared workspaces unless reviewed for sensitive data.— missingTraces can include prompts, completions, tool inputs, tool outputs, errors, costs, tokens, tags, and application metadata. The docs say AgentOps automatically collects basic host environment details such as OS, Python version, anonymized hostname, and SDK version. Hosted dashboard use sends telemetry to AgentOps infrastructure; self-hosted use still requires retention, access-control, and log-review policies.Test cases, traces, spans, prompts, actual outputs, expected outputs, retrieval context, tool arguments, metadata, and evaluation results may contain sensitive user or business data. LLM-based metrics can send evaluation payloads to the configured model provider unless a reviewed local model path is used. DeepEval documentation says evaluations run locally by default, while Confident AI login and cloud reporting are optional paths for centralized results. The official data privacy docs say DeepEval collects basic PostHog telemetry by default, including event names, metric names, notebook usage, an anonymous UUID, and public IP, with `DEEPEVAL_TELEMETRY_OPT_OUT=1` available for opt-out.
Prerequisites— none listed
  • Python environment for running the Evidently library, reports, test suites, or local UI.
  • Dataset, model outputs, LLM application traces, prompts, responses, labels, or other production-aligned examples to evaluate.
  • Reference or baseline data when using drift, regression, or data quality checks.
  • Reviewed metric selection, pass and fail thresholds, alert ownership, and release policy before using results in CI or production monitoring.
— none listed
  • Python or TypeScript/JavaScript application using a supported LLM provider or agent framework.
  • AgentOps project/API key for hosted dashboard use, or a reviewed self-hosted deployment plan.
  • A telemetry policy for which prompts, responses, tool calls, metadata, and host details may be captured.
  • Python environment for installing and running the `deepeval` package in the project being tested.
  • Representative LLM test cases, expected outputs, retrieval context, traces, datasets, or golden examples for the behavior being evaluated.
  • Model provider credentials for LLM-as-a-judge metrics such as G-Eval, Answer Relevancy, or other configured metrics.
  • CI policy for which evaluation thresholds are advisory, which are blocking, and who reviews failures before release decisions.
Install
Config
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimedUnclaimed
  1. 01
    Why it made the cut

    LangSmith is included because it has privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  2. 02
    Why it made the cut

    Evidently is included because it has safety notes present, privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  3. 03
    Why it made the cut

    Arize Phoenix is included because it has source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  4. 04
    Why it made the cut

    AgentOps is included because it has safety notes present, privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  5. 05
    Why it made the cut

    DeepEval is included because it has safety notes present, privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  6. 06
    Why it made the cut

    MLflow is included because it has safety notes present, privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  7. 07
    Why it made the cut

    TruLens is included because it has safety notes present, privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  8. 08
    Why it made the cut

    Langfuse is included because it has privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  9. 09
    Why it made the cut

    Helicone is included because it has privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  10. 10
    Why it made the cut

    Weave is included because it has source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  11. 11
    Why it made the cut

    Agno is included because it has safety notes present, privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  12. 12
    Why it made the cut

    Dagster is included because it has safety notes present, privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  13. 13
    Why it made the cut

    Hugging Face Evaluate is included because it has safety notes present, privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

  14. 14
    Why it made the cut

    Label Studio is included because it has safety notes present, privacy notes present, source-backed source posture.

    Reach for instead

    If this will touch credentials, local files, or production systems, inspect the upstream source first.

Missing a pick? Propose an edit to this list — every change goes through the same review queue as new entries.

Suggest a pick
Weekly · Sundays

Get the weekly brief

One calm read on Claude workflows. Sundays. No tracking pixels.

Unsubscribe any time. No tracking pixels. No partner blasts.