LLM observability: tools for developers

Monitoring, traces, evaluation and quality tracking for LLM applications. An entry can appear under several use cases when its topics or description provide several explicit signals.

Use case

Activity

Sort by

117 entries in this view.

Tool ranking

Ranked by measured growth, normalized across sources. Raw values keep their source-specific window, shown under each tool; a change requires at least two snapshots from the last 7 days.

  1. 1

    MCP
    Active

    AURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on production infrastructure.

    githubmeasured growthOpen source ↗

    254GitHub stars-3 (-1.2 %)
  2. 2
    Active

    🟪 Open-source runtime that ships any LangGraph or Google ADK agent as a production-ready FastAPI service. Bundled , AG-UI copilotkit API, chat UI, 15+ guardrails, MCP, OpenTelemetry, OIDC. One pip install. Self-hosted, no vendor lock-in.

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/Idun-Group/idun-agent-platform ~/.claude/skills/idun-agent-platform

    198GitHub stars-1 (-0.50 %)
  3. 3
    Active

    Self-hosted AI SRE for Kubernetes — zero-instrumentation eBPF observability plus a copilot that fixes issues through guardrailed, self-verifying actions. BYO-LLM, air-gapped capable.

    githubmeasured growthOpen source ↗

    131GitHub stars-4 (-3.0 %)
  4. 4
    Active

    74 open-source Agent Skills for Claude Code and Codex: AI SEO, AEO and GEO, code review with an A-F ship grade, CI gates, AI evals, design systems, conversion copy, Instagram growth, iOS and Android app shipping, creator rights, and…

    githubmeasured growthOpen source ↗

    129GitHub stars-4 (-3.0 %)
  5. 5
    Active

    A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability

    githubmeasured growthOpen source ↗

    105GitHub starsstable
  6. 6

    Skill
    Dormant

    Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effectiveness on LiarBench v0.2.

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/lc198707/anti-lie ~/.claude/skills/anti-lie

    89GitHub starsstable
  7. 7
    Active

    MCP server for Langfuse LLM observability — trace and observation analysis.

    mcpmeasured growthOpen source ↗

    Install claude mcp add langfuse -- npx langfuse-observability-mcp-server

    78GitHub starsstable
  8. 8
    Active

    AgentX python SDK. Build multi-agent AI workforce. Run evaluation. Trace your agent. Full Observability.

    githubmeasured growthOpen source ↗

    68GitHub starsstable
  9. 9
    Active

    Open benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic scoring, pre-registered rubric.

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/aleclindz/seo-skill-bench ~/.claude/skills/seo-skill-bench

    51GitHub stars-5 (-8.9 %)
  10. 10

    Skill
    Active

    Agent skills for Arize — datasets, experiments, and traces via the ax CLI

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/Arize-ai/arize-skills ~/.claude/skills/arize-skills

    47GitHub starsstable
  11. 11
    Active

    Make Claude Opus 4.8 behave like Claude Fable 5 — doctrine output style, drift-catching hooks, and an eval loop against golden Fable transcripts. Claude Code plugin.

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add rennf93/opus-fable-playbook

    33GitHub starsstable
  12. 12
    Dormant

    🔍 AI observability skill for Claude Code. Debug LangChain/LangGraph agents by fetching execution traces from LangSmith Studio directly in your terminal.

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/OthmanAdi/langsmith-fetch-skill ~/.claude/skills/langsmith-fetch-skill

    27GitHub starsstable
  13. 13

    Agent
    Dormant

    Policy-enforced observability and fail-closed guardrails for MCP/A2A multi-agent systems.

    githubmeasured growthOpen source ↗

    26GitHub starsstable
  14. 14
    Active

    Sentry instrumentation skill for system-behavior tracking

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/tortastudios/sentry-instrumentation ~/.claude/skills/sentry-instrumentation

    24GitHub starsstable
  15. 15

    Other
    Active

    AI-detector auditing toolkit: measures how often a detector flags genuine human writing, how stable its verdict is across seeds, and whether that verdict survives meaning-preserving edits. Detector-in-the-loop measurement harness. Claude…

    githubmeasured growthOpen source ↗

    18GitHub starsstable
  16. 16

    Skill
    Active

    Measure prompt and skill improvements with blind A/B comparison.

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add shinpr/rashomon

    18GitHub starsstable
  17. 17
    Active

    Two Claude Code skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique to catch hallucinations), plus a fixture-based eval suite.

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add prime-radiant-inc/parallel-adversarial-review

    17GitHub starsstable
  18. 18
    Active

    Make Claude write clearly, for everyone.

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add stefanobaghino/simple-output-styles

    16GitHub starsstable
  19. 19
    Active

    Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper (audit/elevate READMEs and make a repo open-source-ready).

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add GiustoPiedimonte/agentic-engineering-marketplace

    13GitHub starsstable
  20. 20

    Other
    Dormant

    A Claude Code skill that adds a rubric-based eval layer to any agent project. Framework-agnostic — generates rubric, test cases, judge prompt, and harness. Returns a weighted score plus a judge-leniency signal.

    githubmeasured growthOpen source ↗

    13GitHub starsstable
  21. 21
    Active

    Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.

    mcpmeasured growthOpen source ↗

    Install claude mcp add mcp-server -- npx @spanlens/mcp-server

    12GitHub starsstable
  22. 22

    Skill
    Active

    Turn one decision into a judged tournament of solutions, then pick the best — a Claude Code skill that generates candidates, auto-derives the rubric, judges independently, and returns a defensible winner.

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add CoriChui/bakeoff

    10GitHub starsstable
  23. 23

    Other
    Active

    A Go-native framework for LLM agents, with OpenTelemetry observability built in.

    githubmeasured growthOpen source ↗

    10GitHub starsstable

Learning resources

Ranked by measured growth, normalized across sources. These resources remain available separately and do not take part in the main tool ranking.

  1. 1
    ActiveOpen source ↗

    Curated + scored map of official MCP servers and agents for DevOps, Cloud, SRE, and Platform Engineering — every entry rated on production access, approval gates, and audit evidence.

    githubResourcemeasured growth
    77GitHub starsstable
  2. 2
    ActiveOpen source ↗

    My complete journey to becoming an Agentic AI Engineer through structured learning, projects, experiments, and production-ready implementations of modern AI systems.

    githubResourcemeasured growth
    18GitHub starsstable