@hitl-kit/* — React primitives, Zod event schemas, composable decision gates, and LangGraph / AI-SDK / MCP adapters for human-in-the-loop agentic UIs. Components install via the shadcn CLI; packages live on npm. Part of akaOSS.

Open-science human-in-the-loop tool for searching, annotating, curating legal judgements, reviewing model suggestions with Hypothesis, and exporting project-scoped annotated data

Netz-Werkzeug.Macherei – Defensive Publication zur datensouveränen KI-Architektur

LLM confidence scoring layer — multi-dimensional epistemic verification for source grounding, factual consistency, and claim accuracy across ChatGPT, Claude, Grok, Perplexity, and any LLM output.

Enterprise safety layer for AI agent workflows, built on Mastra — RBAC, audit logs, policy enforcement, approval management, and Cloudflare-native durable execution. Open-source, Apache-2.0.

AI orchestration platform with native human-in-the-loop, MCP support, and built-in governance. MIT licensed.

An LLM-agnostic and runnable supply chain agent to track supply chain disruptions.