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.
- 1Active
skill-receipts
SkillClaude Code skills where every entry ships receipts — accuracy-gated benchmarks against baseline and placebo, rejects published
githubmeasured growthOpen source ↗
Install
git clone https://github.com/sjh9714/skill-receipts ~/.claude/skills/skill-receipts2GitHub starsstable - 2Active
agent-stack
SkillProduction patterns for agent orchestrators, harnesses, evals, MCP/A2A interoperability, memory, provider routing, and LLM usage metering.
githubmeasured growthOpen source ↗
Install
git clone https://github.com/ssheleg/agent-stack ~/.claude/skills/agent-stack2GitHub stars+1 (+100.0 %) - 3Active
pyxen
AgentA lightweight Python library that decouples agentic runtime from applications it builds
githubmeasured growthOpen source ↗
1GitHub starsstable - 4Active
Multi-agent quality gate skill for Claude Code that researches, reviews, tests and challenges AI-generated work before the final answer.
githubmeasured growthOpen source ↗
Install
git clone https://github.com/ma-nucho-pro/supervisor-skill-claude ~/.claude/skills/supervisor-skill-claude2GitHub starsstable - 5Dormant
CustoFlow
OtherMulti-agent customer support system with Google ADK & Gemini 2.5 Flash Lite. Kaggle capstone demonstrating 11+ concepts. Automates 80%+ queries, <10s response time.
githubmeasured growthOpen source ↗
2GitHub starsstable - 6Active
langfuse-docs
Skill🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps
githubmeasured growthOpen source ↗
Install
git clone https://github.com/langfuse/langfuse-docs ~/.claude/skills/langfuse-docs239GitHub stars+3 (+1.3 %) - 7Dormant
Agents-eval
AgentA Multi-Agent System (MAS) evaluation framework using PydanticAI that generates and evaluates scientific paper reviews through a three-tiered assessment approach: traditional metrics, LLM-as-a-Judge, and graph-based complexity analysis.
githubmeasured growthOpen source ↗
2GitHub starsstable - 8Active
boundary-bench
AgentDeterministic crash tests for agent control planes: paired worlds, hard stops, budgets, scopes, approvals, and hash-linked receipts.
githubmeasured growthOpen source ↗
1GitHub starsstable - 9Active
DriftSentinel
AgentAgent 降智检测与自愈公评网络 — an immune system for the AI agent society
githubmeasured growthOpen source ↗
1GitHub starsstable - 10Dormant
A safety-first multi-agent mental health companion with real-time distress tracking, triple-layer guardrails, and evidence-based grounding techniques. Built for Kaggle × Google Agents Intensive 2025 Capstone (Agents for Good Track)
githubmeasured growthOpen source ↗
1GitHub starsstable - 11Active
DeepSeek-Infra
OtherLocal-first Agentic AI Infrastructure Platform with LLM Gateway, Agent DAG Runtime, MCP Tool Hub, A2A Agent Mesh, Local RAG, Tool Sandbox and Observability.
githubmeasured growthOpen source ↗
1GitHub starsstable - 12Dormant
primal-core
AgentThe reliability and interoperability layer for AI agents. A2A-native. MCP-bridged.
githubmeasured growthOpen source ↗
1GitHub starsstable - 13Active
idun-agent-platform
Skill🟪 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-platform198GitHub stars-1 (-0.50 %) - 14Active
historian
AgentA local A2A event and continuity service for agent applications, with structured history, provenance-safe transcripts, literal search, and natural-language queries.
githubmeasured growthOpen source ↗
1GitHub stars+1 - 15Active
Skill instalable para Claude Code que mide si tu agente cumple las reglas establecidas. Lee el historial de sesiones de tu disco y devuelve un porcentaje por regla de cumplimiento. Sin instalar nada, sin red, biblioteca estándar.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add jleonceo/skill-adherencia-reglas1GitHub starsstable - 16Active
adherencia-reglas
SkillMide si tu agente de IA cumple las reglas que le escribiste. Lee el historial local de Claude Code y devuelve un porcentaje por regla. Sin instalar nada, sin red, biblioteca estándar.
githubmeasured growthOpen source ↗
Install
git clone https://github.com/jleonceo/adherencia-reglas ~/.claude/skills/adherencia-reglas1GitHub starsstable - 17Dormant
agentanvil
AgentContract-based testing for LLM agents: hybrid evaluation, multi-agent + A2A, deterministic replay.
githubmeasured growthOpen source ↗
0GitHub starsstable - 18Active
8 MCP SMB products — standalone AI servers for SMBs: Guardrails, FinOps, Observability, Router, Trust Score, Memory, ThinkSecure, A2A Lite. 37 tools, TNC credits billing.
githubmeasured growthOpen source ↗
1GitHub starsstable - 19Active
kubesphere
SkillThe container platform tailored for Kubernetes multi-cloud, datacenter, and edge management ⎈ 🖥 ☁️
githubmeasured growthOpen source ↗
Install
git clone https://github.com/kubesphere/kubesphere ~/.claude/skills/kubesphere17 037GitHub stars+8 (+0.05 %) - 20Active
craft-skills
SkillResearch-backed, eval-driven skills for AI agents
githubmeasured growthOpen source ↗
Install
git clone https://github.com/ZSeven-W/craft-skills ~/.claude/skills/craft-skills142GitHub stars+18 (+14.5 %) - 21Active
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 %) - 22Active
CodeFlow
Agent面向长程研发任务的 Java Agent Harness,支持 A2A 跨语言协作、可恢复执行、上下文工程与 Eval 驱动开发。
githubmeasured growthOpen source ↗
0GitHub starsstable - 23Active
adlc-team-skills
Skill🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams
githubmeasured growthOpen source ↗
Install
git clone https://github.com/tikalk/adlc-team-skills ~/.claude/skills/adlc-team-skills132GitHub stars+1 (+0.76 %) - 24Active
dynatrace-for-ai
SkillSkills, prompts, and instructions for building AI agents on top of Dynatrace production context
githubmeasured growthOpen source ↗
Install
git clone https://github.com/Dynatrace/dynatrace-for-ai ~/.claude/skills/dynatrace-for-ai132GitHub stars+4 (+3.1 %) - 25Active
langfuse-mcp
MCPA 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