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

122 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

    Skill
    Active

    OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

    PythonLicense: Apache-2.0
    • agent
    • agent-skills
    • ai-agent
    • alignment
    • evaluation

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/agentscope-ai/OpenJudge ~/.claude/skills/OpenJudge

    809GitHub stars+6 (+0.75 %)
  2. 2

    Skill
    Active

    Skills, prompts, and instructions for building AI agents on top of Dynatrace production context

    JavaScriptLicense: Apache-2.0
    • agent-skills
    • ai-agents
    • claude-code
    • devops
    • dql

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/Dynatrace/dynatrace-for-ai ~/.claude/skills/dynatrace-for-ai

    132GitHub stars+4 (+3.1 %)
  3. 3

    Skill
    Active

    Vendor-neutral OpenTelemetry skills for AI coding agents, grounded in upstream sources

    ShellLicense: Apache-2.0
    • agent-skills
    • ai
    • observability
    • opentelemetry

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/ollygarden/opentelemetry-agent-skills ~/.claude/skills/opentelemetry-agent-skills

    97GitHub stars+4 (+4.3 %)
  4. 4

    Skill
    Active

    Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters

    PythonLicense: MIT
    • agent-skills
    • evals
    • python
    • skills

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/adewale/skill-eval-harness ~/.claude/skills/skill-eval-harness

    73GitHub stars+4 (+5.8 %)
  5. 5

    Skill
    Active

    🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps

    MDXLicense: MIT
    • agent-skills
    • agents
    • genai
    • hacktoberfest
    • langfuse

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/langfuse/langfuse-docs ~/.claude/skills/langfuse-docs

    239GitHub stars+3 (+1.3 %)
  6. 6

    MCP
    Active

    Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.

    TypeScriptLicense: Apache-2.0
    • agent-management
    • agent-ops
    • agent-orchestration
    • ai-agent-platform
    • ai-agents

    githubmeasured growthOpen source ↗

    50GitHub stars+2 (+4.2 %)
  7. 7

    MCP
    Active

    Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

    HTMLLicense: MIT
    • agent-monitoring
    • agentic-ai
    • ai-agents
    • ai-engineering
    • audit

    githubmeasured growthOpen source ↗

    22GitHub stars+2 (+10.0 %)
  8. 8

    Skill
    Active

    Dashboard for monitoring claude code sessions.

    PythonLicense: Apache-2.0
    • agents
    • agentskills
    • claude-code
    • claude-code-plugin
    • claude-code-skills

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add JayantDevkar/claude-code-karma

    323GitHub stars+2 (+0.62 %)
  9. 9

    Other
    Active

    Open-source observability tool that uses AI agents to self-heal your software

    TypeScriptLicense: Apache-2.0
    • ai
    • llm
    • memory
    • observability
    • opentelemetry

    githubmeasured growthOpen source ↗

    1 404GitHub stars+2 (+0.14 %)
  10. 10

    Other
    Active

    AI SRE AgenticOps for Kubernetes and cloud infrastructure.

    Python
    • agenticops
    • ai
    • aiops
    • aisre
    • cloud

    githubmeasured growthOpen source ↗

    782GitHub stars+1 (+0.13 %)
  11. 11

    Skill
    Active

    Production patterns for agent orchestrators, harnesses, evals, MCP/A2A interoperability, memory, provider routing, and LLM usage metering.

    PythonLicense: MIT
    • a2a
    • agent-orchestration
    • agent-skills
    • ai-agents
    • developer-tools

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/ssheleg/agent-stack ~/.claude/skills/agent-stack

    2GitHub stars+1 (+100.0 %)
  12. 12

    Agent
    Active

    A local A2A event and continuity service for agent applications, with structured history, provenance-safe transcripts, literal search, and natural-language queries.

    PythonLicense: BSD-2-Clause
    • a2a
    • agent-memory
    • ai-agents
    • event-sourcing
    • fastapi

    githubmeasured growthOpen source ↗

    1GitHub stars+1
  13. 13

    Skill
    Active

    🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams

    ShellLicense: MIT
    • adr
    • agent-skills
    • agentic-sdlc
    • ai-coding
    • developer-tools

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/tikalk/adlc-team-skills ~/.claude/skills/adlc-team-skills

    132GitHub stars+1 (+0.76 %)
  14. 14

    MCP
    Active

    Self improving agents through iterations

    PythonLicense: Apache-2.0
    • agent-learning
    • agent-memory
    • agentic-workflows
    • ai-agents
    • claude-code

    githubmeasured growthOpen source ↗

    105GitHub stars+1 (+0.96 %)
  15. 15

    Skill
    Active

    local-first analytics for AI agent skills

    TypeScript
    • agent-skills
    • analytics
    • bun
    • claude-code
    • cli

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/crafter-station/skill-kit ~/.claude/skills/skill-kit

    77GitHub stars+1 (+1.3 %)
  16. 16

    Skill
    Active

    Real-time execution trace and cost intelligence for Claude Code

    TypeScriptLicense: MIT
    • agentic-workflow
    • ai-productivity
    • anthropic
    • anthropic-claude
    • claude

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add DeibyGS/claudestat

    34GitHub stars+1 (+3.0 %)
  17. 17

    Skill
    Active

    A skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baseline-tested generation, per-skill regression evals, ecosystem doctor, cross-runtime compile, and an opt-in proactive advisor.

    PythonLicense: MIT
    • agent-skills
    • claude-ai
    • claude-code
    • claude-skills
    • codex

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/tripleyak/SkillForge ~/.claude/skills/SkillForge

    884GitHub stars+1 (+0.11 %)
  18. 18

    MCP
    Active

    Log Claude Code sessions to Opik, the open-source LLM observability and evaluation platform, built by Comet. Tracing, evaluation, and skills for observable AI applications.

    GoLicense: Apache-2.0
    • ai-agent
    • claude-ai
    • claude-code-plugin
    • llm-observation
    • mcp-server

    githubmeasured growthOpen source ↗

    22GitHub stars+1 (+4.8 %)
  19. 19

    Other
    Active

    A command-line tool to scaffold and manage enterprise-ready AI Agents powered by the A2A (Agent-to-Agent) protocol

    GoLicense: Apache-2.0
    • a2a
    • agents
    • ai
    • containerized
    • docker

    githubmeasured growthOpen source ↗

    14GitHub stars+1 (+7.7 %)
  20. 20

    Skill
    Active

    Production-grade AI coding rules for Cursor and Claude Code. 15 rules + 9 doc templates + skills + agents + MCP setup. Drop into any project.

    PythonLicense: MIT
    • ai-agents
    • ai-coding
    • ai-development
    • ai-engineer
    • automation

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/aiagentwithdhruv/ai-dev-stack ~/.claude/skills/ai-dev-stack

    10GitHub stars+1 (+11.1 %)
  21. 21

    Skill
    Active

    Audit which Claude Code skills you actually use — surface dead installs and hallucinated invocations from your session logs.

    TypeScriptLicense: MIT
    • anthropic
    • audit
    • claude
    • claude-code
    • claude-code-plugin

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add sfrangulov/skill-graveyard

    10GitHub stars+1 (+11.1 %)
  22. 22

    Agent
    Active

    Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory, and observability.

    PythonLicense: Apache-2.0
    • a2a-protocol
    • agentcore
    • agentcore-agent
    • agentcore-gateway
    • agentcore-identity

    githubmeasured growthOpen source ↗

    5GitHub stars+1 (+25.0 %)
  23. 23

    MCP
    Active

    Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

    PythonLicense: Apache-2.0
    • agent-optimization
    • agent-skills
    • agentic-ai
    • ai-agents
    • claude

    githubmeasured growthOpen source ↗

    47GitHub stars+1 (+2.2 %)

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

    awesome-llm-observability

    Skill
    ActiveOpen source ↗

    50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.

    Python
    • ai-agents
    • ai-engineering
    • ai-observability
    • awesome
    • awesome-list
    github

    Install git clone https://github.com/ContextJet-ai/awesome-llm-observability ~/.claude/skills/awesome-llm-observability

    Resourcemeasured growth
    32GitHub stars+2 (+6.7 %)
  2. 2

    trigger_tree

    Skill
    ActiveOpen source ↗

    Documentation-discovery telemetry for Claude Code — heat/cold maps, health grade, evidence-backed router fixes. 100% local, zero tokens. /tt

    PythonLicense: MIT
    • ai-agents
    • claude-code
    • claude-code-plugin
    • docs-as-code
    • documentation
    github

    Install /plugin marketplace add Hedde/trigger_tree

    Resourcemeasured growth
    14GitHub stars+1 (+7.7 %)