Mit Beobachtbarkeit verknüpfte gemessene Katalogeinträge.
🔍 AI observability skill for Claude Code. Debug LangChain/LangGraph agents by fetching execution traces from LangSmith Studio directly in your terminal.
Sterne28Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
MCP server for Langfuse LLM observability — trace and observation analysis.
Downloads · letzte 7 Tage135Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost postures and model tiering, under any rules library or orchestration layer.
Sterne24Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Sentry instrumentation skill for system-behavior tracking
Sterne24Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
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 Code skill + Python CLI. MIT.
Sterne24Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.
Sterne24Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
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.
Sterne23Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as a deny-by-default MCP server. Framework-agnostic, Python 3.11+
Sterne23Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · -4,17% relative Änderung
Watch your Claude Code subagents work as a pixel-art office. Rewind any second, see what every agent cost, and turn any session into a timelapse GIF. Read-only, 100% local.
Sterne22Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Measure prompt and skill improvements with blind A/B comparison.
Sterne19Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung