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。

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
dynatrace-for-ai
技能
活跃最近提交：2 天前 · 2026-08-31
Skills, prompts, and instructions for building AI agents on top of Dynatrace production context
JavaScript许可证: Apache-2.0
- agent-skills
- ai-agents
- claude-code
- devops
- dql
github5 个月前创建实测增长打开来源 ↗
安装 git clone https://github.com/Dynatrace/dynatrace-for-ai ~/.claude/skills/dynatrace-for-ai
132GitHub 星标+6 (+4.8 %)
2
cilium
其他
活跃最近提交：今天 · 2026-09-02
eBPF-based Networking, Security, and Observability
Go许可证: Apache-2.0
- bpf
- cncf
- cni
- containers
- ebpf
github10 年前创建实测增长打开来源 ↗
25 041GitHub 星标+27 (+0.11 %)
3
skill-eval-harness
技能
活跃最近提交：2 天前 · 2026-08-31
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
Python许可证: MIT
- agent-skills
- evals
- python
- skills
github2 个月前创建实测增长打开来源 ↗
安装 git clone https://github.com/adewale/skill-eval-harness ~/.claude/skills/skill-eval-harness
73GitHub 星标+4 (+5.8 %)
4
bar-observatory
MCP
活跃最近提交：5 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
github20 天前创建最新实测增长打开来源 ↗
22GitHub 星标+2 (+10.0 %)
5
nora
MCP
活跃最近提交：1 天前 · 2026-09-01
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+3 (+6.4 %)
6
OpenJudge
技能
活跃最近提交：30 天前 · 2026-08-03
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
Python许可证: Apache-2.0
- agent
- agent-skills
- ai-agent
- alignment
- evaluation
github14 个月前创建实测增长打开来源 ↗
安装 git clone https://github.com/agentscope-ai/OpenJudge ~/.claude/skills/OpenJudge
809GitHub 星标+10 (+1.3 %)
7
opentelemetry-agent-skills
技能
活跃最近提交：今天 · 2026-09-01
Vendor-neutral OpenTelemetry skills for AI coding agents, grounded in upstream sources
Shell许可证: Apache-2.0
- agent-skills
- ai
- observability
- opentelemetry
github6 个月前创建实测增长打开来源 ↗
安装 git clone https://github.com/ollygarden/opentelemetry-agent-skills ~/.claude/skills/opentelemetry-agent-skills
97GitHub 星标+4 (+4.3 %)
8
ai-dev-stack
技能
活跃最近提交：2 个月前 · 2026-06-29
Production-grade AI coding rules for Cursor and Claude Code. 15 rules + 9 doc templates + skills + agents + MCP setup. Drop into any project.
Python许可证: MIT
- ai-agents
- ai-coding
- ai-development
- ai-engineer
- automation
github5 个月前创建实测增长打开来源 ↗
安装 git clone https://github.com/aiagentwithdhruv/ai-dev-stack ~/.claude/skills/ai-dev-stack
10GitHub 星标+1 (+11.1 %)
9
skill-graveyard
技能
活跃最近提交：54 天前 · 2026-07-10
Audit which Claude Code skills you actually use — surface dead installs and hallucinated invocations from your session logs.
TypeScript许可证: MIT
- anthropic
- audit
- claude
- claude-code
- claude-code-plugin
github4 个月前创建实测增长打开来源 ↗
安装 /plugin marketplace add sfrangulov/skill-graveyard
10GitHub 星标+1 (+11.1 %)
10
adl-cli
其他
活跃最近提交：3 天前 · 2026-08-29
A command-line tool to scaffold and manage enterprise-ready AI Agents powered by the A2A (Agent-to-Agent) protocol
Go许可证: Apache-2.0
- a2a
- agents
- ai
- containerized
- docker
github13 个月前创建实测增长打开来源 ↗
14GitHub 星标+1 (+7.7 %)
11
untell
其他
活跃最近提交：今天 · 2026-09-02
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+1 (+5.9 %)
12
kubesphere
技能
活跃最近提交：49 天前 · 2026-07-15
The container platform tailored for Kubernetes multi-cloud, datacenter, and edge management ⎈ 🖥 ☁️
Go
- agent-skills
- ai
- cloud-native
- cncf
- devops
github8 年前创建实测增长打开来源 ↗
安装 git clone https://github.com/kubesphere/kubesphere ~/.claude/skills/kubesphere
17 037GitHub 星标+9 (+0.05 %)
13
opik-claude-code-plugin
MCP
活跃最近提交：33 天前 · 2026-07-30
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.
Go许可证: Apache-2.0
- ai-agent
- claude-ai
- claude-code-plugin
- llm-observation
- mcp-server
github6 个月前创建实测增长打开来源 ↗
22GitHub 星标+1 (+4.8 %)
14
kubeshark
智能体
活跃最近提交：1 天前 · 2026-09-01
eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Go许可证: Apache-2.0
- cloud-native
- devops
- docker
- ebpf
- golang
github5 年前创建实测增长打开来源 ↗
12 066GitHub 星标+7 (+0.06 %)
15
langfuse-docs
技能
活跃最近提交：今天 · 2026-09-02
🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps
MDX许可证: MIT
- agent-skills
- agents
- genai
- hacktoberfest
- langfuse
github3 年前创建实测增长打开来源 ↗
安装 git clone https://github.com/langfuse/langfuse-docs ~/.claude/skills/langfuse-docs
239GitHub 星标+3 (+1.3 %)
16
claude-code-karma
技能
活跃最近提交：3 天前 · 2026-08-30
Dashboard for monitoring claude code sessions.
Python许可证: Apache-2.0
- agents
- agentskills
- claude-code
- claude-code-plugin
- claude-code-skills
github7 个月前创建实测增长打开来源 ↗
安装 /plugin marketplace add JayantDevkar/claude-code-karma
323GitHub 星标+3 (+0.94 %)
17
claudestat
技能
活跃最近提交：2 天前 · 2026-08-30
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+1 (+3.0 %)
18
cap-evolve
MCP
活跃最近提交：6 天前 · 2026-08-27
Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
Python许可证: Apache-2.0
- agent-optimization
- agent-skills
- agentic-ai
- ai-agents
- claude
github2 个月前创建实测增长打开来源 ↗
47GitHub 星标+1 (+2.2 %)
19
SkillForge
技能
活跃最近提交：34 天前 · 2026-07-29
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.
Python许可证: MIT
- agent-skills
- claude-ai
- claude-code
- claude-skills
- codex
github8 个月前创建实测增长打开来源 ↗
安装 git clone https://github.com/tripleyak/SkillForge ~/.claude/skills/SkillForge
884GitHub 星标+3 (+0.34 %)
20
skill-kit
技能
活跃最近提交：1 天前 · 2026-08-31
local-first analytics for AI agent skills
TypeScript
- agent-skills
- analytics
- bun
- claude-code
- cli
github6 个月前创建实测增长打开来源 ↗
安装 git clone https://github.com/crafter-station/skill-kit ~/.claude/skills/skill-kit
77GitHub 星标+1 (+1.3 %)
21
altk-evolve
MCP
活跃最近提交：7 天前 · 2026-08-25
Self improving agents through iterations
Python许可证: Apache-2.0
- agent-learning
- agent-memory
- agentic-workflows
- ai-agents
- claude-code
github8 个月前创建实测增长打开来源 ↗
105GitHub 星标+1 (+0.96 %)
22
superlog
其他
活跃最近提交：3 天前 · 2026-08-30
Open-source observability tool that uses AI agents to self-heal your software
TypeScript许可证: Apache-2.0
- ai
- llm
- memory
- observability
- opentelemetry
github3 个月前创建实测增长打开来源 ↗
1 404GitHub 星标+2 (+0.14 %)
23
adlc-team-skills
技能
活跃最近提交：13 天前 · 2026-08-20
🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams
Shell许可证: MIT
- adr
- agent-skills
- agentic-sdlc
- ai-coding
- developer-tools
github43 天前创建实测增长打开来源 ↗
安装 git clone https://github.com/tikalk/adlc-team-skills ~/.claude/skills/adlc-team-skills
132GitHub 星标+1 (+0.76 %)

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
awesome-llm-observability
技能
活跃最近提交：2 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
2 天前活跃59 天前创建资源实测增长
32GitHub 星标+2 (+6.7 %)
2
trigger_tree
技能
活跃最近提交：1 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
1 天前活跃47 天前创建资源实测增长
14GitHub 星标+1 (+7.7 %)

LLM 可观测性

用途

活跃度

排序方式

工具排名

dynatrace-for-ai

cilium

skill-eval-harness

bar-observatory

nora

OpenJudge

opentelemetry-agent-skills

ai-dev-stack

skill-graveyard

adl-cli

untell

kubesphere

opik-claude-code-plugin

kubeshark

langfuse-docs

claude-code-karma

claudestat

cap-evolve

SkillForge

skill-kit

altk-evolve

superlog

adlc-team-skills

学习与参考资源

awesome-llm-observability

trigger_tree