Die Werkzeugbeschreibungen sind auf Englisch.

LLM-Beobachtbarkeit

Monitoring, Traces, Bewertung und Qualität von LLM-Anwendungen.

Anwendungsfall

Aktivität

Sortieren nach

117

Werkzeug-Rangliste

Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.

  1. 1

    MCP
    Aktiv

    Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.

    ↓ 32 Downloads/WocheTypeScriptLizenz: MIT

      mcpgemessenes WachstumQuelle öffnen ↗

      Installieren claude mcp add mcp-server -- npx @spanlens/mcp-server

      12GitHub-Sternestabil
    • 2

      Sonstige
      Aktiv

      Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI…

      TypeScriptLizenz: MIT
      • ci
      • ci-cd
      • cicd
      • evaluation
      • evaluation-framework

      githubgemessenes WachstumQuelle öffnen ↗

      24 768GitHub-Sterne+142 (+0.58 %)
    • 3

      Sonstige
      Aktiv

      AI SRE AgenticOps for Kubernetes and cloud infrastructure.

      Python
      • agenticops
      • ai
      • aiops
      • aisre
      • cloud

      githubgemessenes WachstumQuelle öffnen ↗

      782GitHub-Sterne+1 (+0.13 %)
    • 4

      Agent
      Aktiv

      The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models…

      PythonLizenz: Apache-2.0
      • agentops
      • agents
      • ai
      • ai-governance
      • apache-spark

      githubgemessenes WachstumQuelle öffnen ↗

      27 783GitHub-Sterne+82 (+0.30 %)
    • 5

      Bibliothek
      Aktiv

      Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

      PythonLizenz: Apache-2.0
      • automation
      • data
      • data-engineering
      • data-ops
      • data-science

      githubgemessenes WachstumQuelle öffnen ↗

      23 766GitHub-Sterne+66 (+0.28 %)
    • 6

      Sonstige
      Aktiv

      A high-performance observability data pipeline.

      RustLizenz: MPL-2.0
      • agent
      • cloud-native
      • data-transformation
      • datadog
      • etl

      githubgemessenes WachstumQuelle öffnen ↗

      22 509GitHub-Sterne+40 (+0.18 %)
    • 7

      Sonstige
      Aktiv

      Open source observability platform for logs, metrics, traces, frontend monitoring, pipelines and LLM observability. A sophisticated, simple and highly performant alternative to Datadog, Splunk, and Elasticsearch with 140x lower storage…

      TypeScriptLizenz: AGPL-3.0
      • analytics
      • apm
      • datadog
      • elasticsearch
      • grafana

      githubgemessenes WachstumQuelle öffnen ↗

      21 615GitHub-Sterne+96 (+0.45 %)
    • 8

      Sonstige
      Aktiv

      SigNoz is an open-source, OpenTelemetry-native observability platform for your team and their AI agents. Get logs, metrics, and traces in one tool with features like APM, distributed tracing, log management, infra monitoring, etc. Combined…

      TypeScript
      • apm
      • application-monitoring
      • distributed-tracing
      • go
      • good-first-issue

      githubgemessenes WachstumQuelle öffnen ↗

      32 003GitHub-Sterne+50 (+0.16 %)
    • 9

      Sonstige
      Aktiv

      Mastra is the modern TypeScript framework for AI-powered applications and agents.

      TypeScript
      • agents
      • ai
      • chatbots
      • evals
      • javascript

      githubgemessenes WachstumQuelle öffnen ↗

      27 658GitHub-Sterne+128 (+0.46 %)
    • 10

      Sonstige
      Aktiv

      The fastest path to AI-powered full stack observability, even for lean teams.

      GoLizenz: GPL-3.0
      • ai
      • alerting
      • cncf
      • data-visualization
      • database

      githubgemessenes WachstumQuelle öffnen ↗

      80 412GitHub-Sterne+85 (+0.11 %)
    • 11

      MCP
      Aktiv

      🫖 Status page with uptime monitoring & API monitoring as code 🫖

      TypeScriptLizenz: AGPL-3.0
      • alerting
      • incident-management
      • mcp
      • mcp-server
      • monitoring

      githubgemessenes WachstumQuelle öffnen ↗

      9 056GitHub-Sterne+31 (+0.34 %)
    • 12

      Sonstige
      Aktiv

      Self-hosted AI SRE for Kubernetes — zero-instrumentation eBPF observability plus a copilot that fixes issues through guardrailed, self-verifying actions. BYO-LLM, air-gapped capable.

      GoLizenz: Apache-2.0
      • ai-agent
      • aiops
      • clickhouse
      • devops
      • ebpf

      githubgemessenes WachstumQuelle öffnen ↗

      131GitHub-Sterne-4 (-3.0 %)
    • 13

      Sonstige
      Aktiv

      eBPF-based Networking, Security, and Observability

      GoLizenz: Apache-2.0
      • bpf
      • cncf
      • cni
      • containers
      • ebpf

      githubgemessenes WachstumQuelle öffnen ↗

      25 047GitHub-Sterne+29 (+0.12 %)
    • 14

      Agent
      Aktiv

      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.

      GoLizenz: Apache-2.0
      • cloud-native
      • devops
      • docker
      • ebpf
      • golang

      githubgemessenes WachstumQuelle öffnen ↗

      12 068GitHub-Sterne+8 (+0.07 %)
    • 15

      Agent
      Aktiv

      DataBuff is an AI-native APM built on Opentelemetry，with multi-agent troubleshooting out of the box.

      JavaLizenz: AGPL-3.0
      • aiops
      • apm
      • application-monitoring
      • devops
      • distributed-tracing

      githubgemessenes WachstumQuelle öffnen ↗

      642GitHub-Sterne+32 (+5.2 %)
    • 16

      Sonstige
      Aktiv

      Evidence-first infrastructure for reproducible, isolated executable evaluation and online rewards.

      PythonLizenz: Apache-2.0
      • benchmark
      • kubernetes
      • llm-evaluation
      • llm-infrastructure
      • ray

      githubgemessenes WachstumQuelle öffnen ↗

      140GitHub-Sterne+24 (+20.7 %)
    • 17

      Skill
      Aktiv

      The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

      PythonLizenz: MIT
      • agent-skills
      • ai-agents
      • claude
      • claude-code
      • claude-md

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren git clone https://github.com/Sahir619/fable-method ~/.claude/skills/fable-method

      2 272GitHub-Sterne+16 (+0.71 %)
    • 18

      Agent
      Aktiv

      The Operating System for Scalable Enterprise AI Agents - Run, orchestrate, and deploy Compliant Enterprise AI Agents at scale across frameworks, without lock-in, rewrites or fragile glue code. Native support for MCP, A2A. Interface with all…

      PythonLizenz: Apache-2.0
      • a2a
      • adk
      • ai-agents
      • aws
      • azure

      githubgemessenes WachstumQuelle öffnen ↗

      156GitHub-Sterne+19 (+13.9 %)
    • 19

      MCP
      Aktiv

      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…

      PythonLizenz: Apache-2.0
      • a2a-protocol
      • agent-to-agent
      • ai-agents
      • async-python
      • autoscaling

      githubgemessenes WachstumQuelle öffnen ↗

      3GitHub-Sternestabil
    • 20

      Skill
      Ruhend

      An assembly line for AI software development. 35 skills, 11 agent personas, 29 commands. From raw idea to shipped code.

      ShellLizenz: MIT
      • agentic-engineering
      • agents
      • claude-code
      • claude-code-plugin
      • claude-code-skills

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren /plugin marketplace add aneja5/forge-skills

      3GitHub-Sternestabil
    • 21

      MCP
      Aktiv

      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

      githubgemessenes WachstumQuelle öffnen ↗

      0GitHub-Sternestabil
    • 22

      Agent
      Aktiv

      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.

      Python
      • a2a-protocol
      • anthropic
      • aws-bedrock
      • aws-lambda
      • bedrock-agentcore

      githubgemessenes WachstumQuelle öffnen ↗

      3GitHub-Sternestabil
    • 23

      MCP
      Aktiv

      AURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on production infrastructure.

      RustLizenz: Apache-2.0
      • a2a
      • ai-agent-framework
      • ai-agents
      • ai-sre
      • aiops

      githubgemessenes WachstumQuelle öffnen ↗

      254GitHub-Sterne-3 (-1.2 %)
    • 24

      Agent
      Aktiv

      Generic DeepSeek Harness (dsh) plugins: A2A protocol server, session storage mirror, and Langfuse observability.

      TypeScriptLizenz: MIT
      • agent2agent
      • ai-agents
      • cordis
      • deepseek-harness
      • dsh

      githubgemessenes WachstumQuelle öffnen ↗

      1GitHub-Sternestabil
    • 25

      MCP
      Aktiv

      A typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.

      Shell
      • a2a
      • agent-framework
      • agentic-ai
      • ai
      • ai-agents

      githubgemessenes WachstumQuelle öffnen ↗

      2GitHub-Sternestabil