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

118

工具排名

Ranked by known GitHub stars, highest first; archived repositories come after maintained repositories. 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. 1

    智能体
    活跃

    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

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  2. 2

    智能体
    活跃

    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

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  3. 3

    技能
    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.

    Python许可证: MIT
    • ai-evaluation
    • claude
    • claude-code
    • claude-code-plugin
    • claude-code-skill

    github实测增长打开来源 ↗

    安装 /plugin marketplace add jleonceo/skill-adherencia-reglas

    1GitHub 星标稳定
  4. 4

    智能体
    活跃

    Agent 降智检测与自愈公评网络 — an immune system for the AI agent society

    TypeScript许可证: MIT
    • a2a
    • agent
    • agent-guard
    • ai-sre
    • drift-detection

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  5. 5

    其他
    活跃

    Terminal-first validation harness for reviewing PRDs, RFCs, strategy docs, and experiment plans.

    TypeScript
    • ai-agents
    • claude-code
    • claude-code-skills
    • cli
    • evals

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  6. 6

    智能体
    活跃

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

    Python许可证: BSD-2-Clause
    • a2a
    • agent-memory
    • ai-agents
    • event-sourcing
    • fastapi

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  7. 7

    技能
    活跃

    Run many AIs on one board and keep control of all of it. Deterministic code decides who acts — never a model. A privacy floor keeps sensitive work on your machine, your own tests decide what counts as done, and every action lands on a…

    • a2a
    • agent-orchestration
    • agent-skills
    • ai-agents
    • ai-governance

    github实测增长打开来源 ↗

    安装 git clone https://github.com/sandhusukhdeep2/sc-prism-releases ~/.claude/skills/sc-prism-releases

    1GitHub 星标稳定
  8. 8

    技能
    活跃

    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

    github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
  9. 9

    其他
    活跃

    🔑 HomeStream · 家园·流 — 零成本自托管多Agent协作框架，通往AI世界的那把钥匙 | Zero-cost self-hosted multi-agent framework — The key to AI world

    Python许可证: MIT
    • a2a-protocol
    • agent-framework
    • ai
    • causal-memory
    • event-stream

    github实测增长打开来源 ↗

    0GitHub 星标稳定
  10. 10

    MCP
    活跃

    Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

    Python许可证: MIT

      mcp实测增长打开来源 ↗

      安装 claude mcp add ai-guardian -- uvx ai-guardian-aiops

      0GitHub 星标稳定
    • 11

      智能体
      休眠

      Contract-based testing for LLM agents: hybrid evaluation, multi-agent + A2A, deterministic replay.

      Python许可证: MIT
      • a2a
      • agents
      • contracts
      • evaluation
      • llm

      github实测增长打开来源 ↗

      0GitHub 星标稳定
    • 12

      智能体
      休眠

      OpenTelemetry semantic conventions and instrumentation for agent provenance, derivation lineage, and acceptance criteria evaluation. Fills the Microsoft AI stack observability gap.

      Python
      • a2a-protocol
      • agentic-ai
      • ai-agents
      • observability
      • opentelemetry

      github实测增长打开来源 ↗

      0GitHub 星标稳定
    • 13

      MCP
      活跃

      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

      github实测增长打开来源 ↗

      0GitHub 星标稳定
    • 14

      智能体
      活跃

      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

      github实测增长打开来源 ↗

      0GitHub 星标稳定
    • 15

      MCP
      活跃

      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

      github实测增长打开来源 ↗

      0GitHub 星标稳定
    • 16

      智能体
      活跃

      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。

      Java许可证: Apache-2.0
      • a2a
      • agentic-ai
      • ai-agents
      • developer-tools
      • evals

      github实测增长打开来源 ↗

      0GitHub 星标稳定
    • 17

      智能体
      休眠

      A Python proof-of-concept for tracing multi-turn Agent-to-Agent (A2A) conversations as a single unified MLflow trace for LLM observability and evaluation.

      Python
      • a2a
      • agent-to-agent
      • ai-agents
      • conversational-ai
      • llm-evaluation

      github实测增长打开来源 ↗

      0GitHub 星标稳定

    学习与参考资源

    Ranked by known GitHub stars, highest first; archived repositories come after maintained repositories. 这些资源可单独访问，不参与主要排名。

    1. 1

      production-ai-engineering

      智能体
      活跃打开来源 ↗

      Handbook técnico aberto sobre engenharia de IA em produção: ML tradicional, LLMs, RAG, agentes, segurança, observabilidade, FinOps e deployment.

      Markdown
      • a2a-protocol
      • agentic-ai
      • ai
      • ai-agents
      • ai-engineering
      github资源实测增长
      1GitHub 星标稳定