Mit Beobachtbarkeit verknüpfte gemessene Katalogeinträge.
A Multi-Agent System (MAS) evaluation framework using PydanticAI that generates and evaluates scientific paper reviews through a three-tiered assessment approach: traditional metrics, LLM-as-a-Judge, and graph-based complexity analysis.
Sterne2Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Vendor-neutral OpenTelemetry tracing for A2A agents and MCP services, with W3C context propagation and privacy-safe telemetry.
Sterne2Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Every AI session ends — usually with a wasted paragraph or silence. /wrap closes it with the outcome instead: tell the model how its work turned out, get one emoji back, and the record carries into the next session. Visible in memory, never a training reward. Open spec + prompts for every major tool. MIT.
Sterne2Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Rules, skills and a destructive-SQL seatbelt that keep AI coding agents (Claude Code, Codex, Cursor, Gemini CLI, Copilot) from scanning, overwriting or inventing data. With a 162-run DuckDB eval.
Sterne2Gemessen · 20.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Provide clear documentation for AgentStack’s MCP protocol, plugins, and ecosystem API with usage examples and tool references.
Sterne1Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Deterministic crash tests for agent control planes: paired worlds, hard stops, budgets, scopes, approvals, and hash-linked receipts.
Sterne1Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
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.
Sterne1Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
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 have.
Sterne1Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
8 MCP SMB products — standalone AI servers for SMBs: Guardrails, FinOps, Observability, Router, Trust Score, Memory, ThinkSecure, A2A Lite. 37 tools, TNC credits billing.
Sterne1Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
A safety-first multi-agent mental health companion with real-time distress tracking, triple-layer guardrails, and evidence-based grounding techniques. Built for Kaggle × Google Agents Intensive 2025 Capstone (Agents for Good Track)
Sterne1Gemessen · 21.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung