A

agentic-ai

The unified foundation where your agents, full-stack applications, and data live together.

Prassi operative di Opencity Labs come Claude Code skills installabili

Populates an empty Git repository with scaffolding files and folders for development of CLI tools, libraries, and (micro) services for C++, Go, and Java. The pre-populated repository is prepared for specification driven development with support of an AI coding assistant (Claude Code and GitHub Copilot, albeit to a lesser degree).

An interactive Kubernetes incident-response training simulator built with Godot 4.6, n8n Cloud and the OpenAI API. Learners investigate simulated Kubernetes failures through a visual cluster topology, a controlled kubectl terminal and an adaptive AI incident commander. The simulator records actions, changes the incident over time, assesses the final diagnosis and builds a persistent competency profile across multiple scenarios.

Trustworthy AI assistant that runs 100% on your hardware. Stay in control of your data, costs and dependencies.

create and manage isolated operating workspaces for agentic ai workloads

10 hands-on demos for agentic AI security: blind verification, AIBOM, eval invariants, authority confinement, recon/malware/LFI/SSRF/scan — offline only.

See cache health, context fill, token burn, rate limits, and peak hours in Claude Code CLI.

Find release-order failures that green MR CI misses. GitLab Duo proposes falsifiable experiments; GitLab CI proves evidence-backed release waves.

Terminal-based AI coding assistant with Claude/OpenAI support, secure local tools, web search, and MCP integrations.

Authorization and execution control for AI agents — independent policy and judge approval before consequential tool actions execute. MCP gateway, capability tokens, auditability, and fail-closed execution.

Two independent keys must turn before an AI agent can act. JSON policy-based enforcement, LLM-based judge, short-lived token for tool access. Apache-2.0 concept package.

MCP server + harness for the Linux edition of Sid Meiers Civilization V: Brave New World. Allows agentic models to see and play the game the same way a human would - fog of war, diplomacy, pesky barbarians. Does not enable model to control background AIs.

JSON Schema-driven HTTP(S) active Man in the Middle (MITM) proxy for application-layer inspection, filtering, and modification. Parses JSON and other structured web payloads into JSON-like forms for schema-based matching, filtering, and rewriting. Built on mitmproxy; targeting credential brokering and egress controls for sandboxed AI agents.

Curated resources for AI coding agents, autonomous coding tools, and agentic software engineering.

Yana AI 🐰 One runtime. Any AI. Human-governed. A local-first, cross-platform system for running, connecting, orchestrating, and governing AI — with deterministic control over what it can access, change, and execute. Your AI can act. But who decides how far it can go? yana.vutam.link

Curated Model Context Protocol (MCP) servers, clients, and tooling for agentic systems.

Genesis Cube or Squid Cube? — A dual-use framework for artificial collective organisms. Version 1.0 · DOI 10.5281/zenodo.22854142

Seven evidence-first tools for bounded AI-agent decisions, resumable runs, cross-agent handoffs, verification, and reviewable releases.

GitLab CI/CD component for running Klarent end-to-end tests against your application. Know more at http://klarent.ai/