工具说明为英文。
LLM 可观测性
LLM 应用的监控、追踪、评估和质量管理。
用途
活跃度
排序方式
123
工具排名
按实测增长排序，并在不同来源间归一化。 原始值保留各自的数据窗口；计算变化需要 7 天内至少两次测量。
- 1活跃
galdor
其他A Go-native framework for LLM agents, with OpenTelemetry observability built in.
github实测增长打开来源 ↗
10GitHub 星标稳定 - 2休眠
Local open-source dev tool to debug, secure, and evaluate LLM agents. Provides static analysis, dynamic security checks, and runtime monitoring - integrates with Cursor and Claude Code.
github实测增长打开来源 ↗
安装
/plugin marketplace add cylestio/agent-inspector9GitHub 星标稳定 - 3活跃
anchor
技能Anchor — the production-grade AGENTS.md template for AI coding agents. 51 sections of battle-tested rules. Keep your agents grounded.
github实测增长打开来源 ↗
安装
git clone https://github.com/peva3/anchor ~/.claude/skills/anchor8GitHub 星标稳定 - 4休眠
A self-improving harness router for Claude Code.
github实测增长打开来源 ↗
安装
/plugin marketplace add SeongwoongCho/adaptive-harness8GitHub 星标稳定 - 5活跃
memroos
智能体MemroOS / memroos: memory OS and governance layer for AI agents, agent workflows, dispatch, proof, and context continuity.
github实测增长打开来源 ↗
7GitHub 星标稳定 - 6活跃
axiom
技能Axiom is a curated marketplace of shared plugins for Claude Code and Codex.
github实测增长打开来源 ↗
安装
git clone https://github.com/netopsengineer/axiom ~/.claude/skills/axiom5GitHub 星标稳定 - 73GitHub 星标稳定
- 8活跃
Production reliability, benchmarking, and evaluation layer for MCP agent runtimes — protocol negotiation, A2A interop, circuit breakers, connection pooling, adaptive streaming, and autoscaling, with measured throughput/latency and a…
github实测增长打开来源 ↗
3GitHub 星标稳定 - 9活跃
sre-on-call
智能体Multi-agent SRE on-call investigator that auto-triages Slack/Discord infrastructure alerts via AWS Bedrock AgentCore, fanning out to specialized agents (CloudWatch, EKS, Slack/Discord scanners) for parallel investigation.
github实测增长打开来源 ↗
3GitHub 星标稳定 - 10休眠
An assembly line for AI software development. 35 skills, 11 agent personas, 29 commands. From raw idea to shipped code.
github实测增长打开来源 ↗
安装
/plugin marketplace add aneja5/forge-skills3GitHub 星标稳定 - 11活跃
Claude Code skills where every entry ships receipts — accuracy-gated benchmarks against baseline and placebo, rejects published
github实测增长打开来源 ↗
安装
git clone https://github.com/sjh9714/skill-receipts ~/.claude/skills/skill-receipts2GitHub 星标稳定 - 12活跃
Multi-agent customer support system with Google ADK & Gemini 2.5 Flash Lite. Kaggle capstone demonstrating 11+ concepts. Automates 80%+ queries, <10s response time.
github实测增长打开来源 ↗
2GitHub 星标稳定 - 13休眠
Agents-eval
智能体A 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.
github实测增长打开来源 ↗
2GitHub 星标稳定 - 14活跃
Multi-agent quality gate skill for Claude Code that researches, reviews, tests and challenges AI-generated work before the final answer.
github实测增长打开来源 ↗
安装
git clone https://github.com/ma-nucho-pro/supervisor-skill-claude ~/.claude/skills/supervisor-skill-claude2GitHub 星标稳定 - 15活跃
nudge
MCPA typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.
github实测增长打开来源 ↗
2GitHub 星标稳定 - 16活跃
Mide 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.
github实测增长打开来源 ↗
安装
git clone https://github.com/jleonceo/adherencia-reglas ~/.claude/skills/adherencia-reglas1GitHub 星标稳定 - 17休眠
primal-core
智能体The reliability and interoperability layer for AI agents. A2A-native. MCP-bridged.
github实测增长打开来源 ↗
1GitHub 星标稳定 - 18活跃
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.
github实测增长打开来源 ↗
安装
/plugin marketplace add jleonceo/skill-adherencia-reglas1GitHub 星标稳定 - 191GitHub 星标稳定
- 20活跃
Local-first Agentic AI Infrastructure Platform with LLM Gateway, Agent DAG Runtime, MCP Tool Hub, A2A Agent Mesh, Local RAG, Tool Sandbox and Observability.
github实测增长打开来源 ↗
1GitHub 星标稳定 - 21休眠
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)
github实测增长打开来源 ↗
1GitHub 星标稳定 - 22活跃
a2a-otel-kit
MCPVendor-neutral OpenTelemetry tracing for A2A agents and MCP services, with W3C context propagation and privacy-safe telemetry.
github实测增长打开来源 ↗
1GitHub 星标稳定 - 23活跃
headsup
技能Glanceable Claude Code and Codex state in your terminal tabs: white=idle, blue=working, orange=waiting. Multi-terminal (iTerm2, WezTerm, AI Power Term), a live status bar with Anthropic usage limits, /sfl and /nil window save-and-restore,…
github实测增长打开来源 ↗
安装
git clone https://github.com/wasulajr/headsup ~/.claude/skills/headsup1GitHub 星标稳定 - 24活跃
Terminal-first validation harness for reviewing PRDs, RFCs, strategy docs, and experiment plans.
github实测增长打开来源 ↗
1GitHub 星标稳定
学习与参考资源
按实测增长排序，并在不同来源间归一化。 这些资源可单独访问，不参与主要排名。
- 1活跃打开来源 ↗
tunelab
技能Claude Code plugin for LLM fine-tuning, distillation, and evaluation — decide whether you need fine-tuning at all, distill your LLM logs into small local models (MLX/LoRA), evaluate with held-out discipline, and learn the why at every step.
github安装
资源实测增长/plugin marketplace add rchaz/tunelab6GitHub 星标稳定