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。

工具排名

混合排名：实测增长优先。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
multi-agent-credit-desk
MCP
活跃最近提交：26 天前 · 2026-08-09
Architecture-first Python scaffold for an auditable multi-agent corporate credit desk using A2A, MCP, deterministic credit policies, model routing, and OpenTelemetry.
Python
- a2a-protocol
- agentic-ai
- auditability
- clean-architecture
- credit-risk
github51 天前创建实测增长打开来源 ↗
0GitHub 星标稳定
2
agent-mmm
技能
活跃最近提交：1 天前 · 2026-09-03
Marketing Mix Model expert agent plugin for Claude Code - pymc-marketing v0.18.2+
Python
- claude-code-agent
- claude-code-plugin
- claude-code-skill
- data-analysis
- data-analytics
github5 个月前创建实测增长打开来源 ↗
安装 /plugin marketplace add Yakoub-ai/agent-mmm
4GitHub 星标稳定
3
AI Guardian
MCP
活跃最近提交：2 天前 · 2026-09-02
Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.
Python许可证: MIT
mcp54 天前创建实测增长打开来源 ↗
安装 claude mcp add ai-guardian -- uvx ai-guardian-aiops
0GitHub 星标稳定
4
evoagent-os
智能体
活跃最近提交：25 天前 · 2026-08-10
Local-first control plane for durable, governed agent teams: DAG orchestration, approvals, memory, signed skills, trace contracts, and realtime.
Python许可证: Apache-2.0
- a2a-protocol
- agentic-ai
- ai-agents
- fastapi
- llmops
github26 天前创建最新实测增长打开来源 ↗
0GitHub 星标稳定
5
boundary-bench
智能体
活跃最近提交：2 天前 · 2026-09-02
Deterministic crash tests for agent control planes: paired worlds, hard stops, budgets, scopes, approvals, and hash-linked receipts.
TypeScript许可证: Apache-2.0
- a2a
- agent-evaluation
- ai-agents
- benchmark
- deterministic-replay
github45 天前创建实测增长打开来源 ↗
1GitHub 星标稳定
6
headsup
技能
活跃最近提交：17 天前 · 2026-08-18
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,…
Shell许可证: MIT
- ai-workflow-observability
- claude-code
- claude-code-hooks
- claude-code-skill
- claude-code-skills
github3 个月前创建实测增长打开来源 ↗
安装 git clone https://github.com/wasulajr/headsup ~/.claude/skills/headsup
1GitHub 星标稳定
7
dsh-plugins
智能体
活跃最近提交：6 天前 · 2026-08-29
Generic DeepSeek Harness (dsh) plugins: A2A protocol server, session storage mirror, and Langfuse observability.
TypeScript许可证: MIT
- agent2agent
- ai-agents
- cordis
- deepseek-harness
- dsh
github16 天前创建最新实测增长打开来源 ↗
1GitHub 星标稳定
8
a2a-otel-kit
MCP
活跃最近提交：24 天前 · 2026-08-11
Vendor-neutral OpenTelemetry tracing for A2A agents and MCP services, with W3C context propagation and privacy-safe telemetry.
Python许可证: MIT
- a2a
- agent2agent
- agentic-ai
- ai-agents
- clean-architecture
github50 天前创建实测增长打开来源 ↗
1GitHub 星标稳定
9
nora
MCP
活跃最近提交：1 天前 · 2026-09-03
Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.
TypeScript许可证: Apache-2.0
- agent-management
- agent-ops
- agent-orchestration
- ai-agent-platform
- ai-agents
github5 个月前创建实测增长打开来源 ↗
50GitHub 星标+2 (+4.2 %)
10
claudestat
技能
活跃最近提交：2 天前 · 2026-09-02
Real-time execution trace and cost intelligence for Claude Code
TypeScript许可证: MIT
- agentic-workflow
- ai-productivity
- anthropic
- anthropic-claude
- claude
github4 个月前创建实测增长打开来源 ↗
安装 /plugin marketplace add DeibyGS/claudestat
34GitHub 星标稳定
11
tulip-agents
智能体
活跃最近提交：9 天前 · 2026-08-26
The agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already…
Python许可证: Apache-2.0
- a2a
- agent-framework
- ai-agents
- ai-governance
- ai-safety
github2 个月前创建实测增长打开来源 ↗
1GitHub 星标稳定
12
DeepSeek-Infra
其他
活跃最近提交：2 天前 · 2026-09-02
Local-first Agentic AI Infrastructure Platform with LLM Gateway, Agent DAG Runtime, MCP Tool Hub, A2A Agent Mesh, Local RAG, Tool Sandbox and Observability.
Python
- a2a
- agent-runtime
- ai-infra
- deepseek
- fastapi
github3 个月前创建实测增长打开来源 ↗
1GitHub 星标稳定
13
agentgateway
MCP
活跃最近提交：3 天前 · 2026-09-01
AgentGateway — independent third-party profile of a public API surface, by API Evangelist. AgentGateway is an open-source, AI-native proxy and gateway for routing, observing, and governing traffic to and from AI agents, LLM providers, and…
- agent-to-agent
- ai-gateway
- api-gateway
- apis-json
- cncf
github5 个月前创建实测增长打开来源 ↗
0GitHub 星标稳定
14
bar-observatory
MCP
活跃最近提交：8 天前 · 2026-08-27
Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.
HTML许可证: MIT
- agent-monitoring
- agentic-ai
- ai-agents
- ai-engineering
- audit
github23 天前创建最新实测增长打开来源 ↗
22GitHub 星标+2 (+10.0 %)
15
nudge
MCP
活跃最近提交：14 天前 · 2026-08-21
A typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.
Shell
- a2a
- agent-framework
- agentic-ai
- ai
- ai-agents
github50 天前创建实测增长打开来源 ↗
2GitHub 星标稳定
16
untell
其他
活跃最近提交：2 天前 · 2026-09-03
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…
Python许可证: MIT
- ai-detection
- ai-detector
- benchmark
- claude-code
- claude-code-skill
github2 个月前创建实测增长打开来源 ↗
18GitHub 星标稳定
17
supervisor-skill-claude
技能
活跃最近提交：21 天前 · 2026-08-14
Multi-agent quality gate skill for Claude Code that researches, reviews, tests and challenges AI-generated work before the final answer.
- agentic-coding
- agentic-workflow
- ai-agent-skills
- ai-code-review
- ai-workflows
github21 天前创建最新实测增长打开来源 ↗
安装 git clone https://github.com/ma-nucho-pro/supervisor-skill-claude ~/.claude/skills/supervisor-skill-claude
2GitHub 星标稳定
18
rashomon
技能
活跃最近提交：5 天前 · 2026-08-30
Measure prompt and skill improvements with blind A/B comparison.
Python许可证: MIT
- agent-skills
- ai-tools
- claude-code
- claude-code-plugin
- claude-code-skill
github7 个月前创建实测增长打开来源 ↗
安装 /plugin marketplace add shinpr/rashomon
18GitHub 星标稳定
19
agent-stack
技能
活跃最近提交：3 天前 · 2026-09-01
Production patterns for agent orchestrators, harnesses, evals, MCP/A2A interoperability, memory, provider routing, and LLM usage metering.
Python许可证: MIT
- a2a
- agent-orchestration
- agent-skills
- ai-agents
- developer-tools
github29 天前创建最新实测增长打开来源 ↗
安装 git clone https://github.com/ssheleg/agent-stack ~/.claude/skills/agent-stack
2GitHub 星标+1 (+100.0 %)
20
deslop-GPT
技能
活跃最近提交：1 天前 · 2026-09-03
Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.
Python许可证: MIT
- agent-skills
- claude
- claude-ai
- claude-code
- claude-skills
github12 天前创建最新实测增长打开来源 ↗
安装 git clone https://github.com/MrZoyo/deslop-GPT ~/.claude/skills/deslop-GPT
76GitHub 星标+48 (+171.4 %)
21
mini-program-engineering-skill-suite
技能
活跃最近提交：4 天前 · 2026-09-01
Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product…
Python许可证: MIT
- agent-skills
- ai-agents
- alipay
- ci-cd
- claude-code
github22 天前创建最新实测增长打开来源 ↗
安装 git clone https://github.com/NocodeMrLi/mini-program-engineering-skill-suite ~/.claude/skills/mini-program-engineering-skill-suite
43GitHub 星标+4 (+10.3 %)
22
agent-skills-platform
技能
活跃最近提交：1 天前 · 2026-09-03
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.
Python许可证: MIT
- agent-skills
- ai-agents
- claude-code
- codex
- cursor
github10 个月前创建估算动量打开来源 ↗
安装 git clone https://github.com/FrancyJGLisboa/agent-skills-platform ~/.claude/skills/agent-skills-platform
2 376GitHub 星标—

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
trigger_tree
技能
活跃最近提交：3 天前 · 2026-09-01打开来源 ↗
Documentation-discovery telemetry for Claude Code — heat/cold maps, health grade, evidence-backed router fixes. 100% local, zero tokens. /tt
Python许可证: MIT
- ai-agents
- claude-code
- claude-code-plugin
- docs-as-code
- documentation
github
安装 /plugin marketplace add Hedde/trigger_tree
3 天前活跃49 天前创建资源实测增长
14GitHub 星标+1 (+7.7 %)
2
awesome-llm-observability
技能
活跃最近提交：4 天前 · 2026-08-31打开来源 ↗
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
安装 git clone https://github.com/ContextJet-ai/awesome-llm-observability ~/.claude/skills/awesome-llm-observability
4 天前活跃2 个月前创建资源实测增长
33GitHub 星标+3 (+10.0 %)
3
Agentic_AI_Engineer
智能体
活跃最近提交：3 天前 · 2026-09-01打开来源 ↗
My complete journey to becoming an Agentic AI Engineer through structured learning, projects, experiments, and production-ready implementations of modern AI systems.
Jupyter Notebook许可证: MIT
- a2a-protocol
- agent-orchestration
- ai-guardrails
- fastapi
- kubernetes
github3 天前活跃40 天前创建资源实测增长
18GitHub 星标稳定

LLM 可观测性

用途

活跃度

排序方式

工具排名

multi-agent-credit-desk

agent-mmm

AI Guardian

evoagent-os

boundary-bench

headsup

dsh-plugins

a2a-otel-kit

nora

claudestat

tulip-agents

DeepSeek-Infra

agentgateway

bar-observatory

nudge

untell

supervisor-skill-claude

rashomon

agent-stack

deslop-GPT

mini-program-engineering-skill-suite

agent-skills-platform

学习与参考资源

trigger_tree

awesome-llm-observability

Agentic_AI_Engineer