A

ai-agents

Nord / Forge — git-native agent evolution with auto-commit. Private.

Before/after screenshots for GitLab UI merge requests: captured locally in a GDK checkout, verified, attached to the MR. Agent-agnostic (AGENTS.md); installable as a Claude Code plugin; no dependencies beyond the gitlab repo itself.

AI Agent Guidelines and Infrastructure for Eiseron

VectorForge is a modular, cross-platform digital twin and runtime validation system designed to safely simulate, test, and verify applications, AI models, and system changes before deployment. It creates isolated replicas of real environments to ensure reproducible execution, detect conflicts early, and generate detailed performance and compatibility reports—enabling safer, more reliable software and infrastructure deployment across any system.

ThreadGraph is an open-source, AGPL-3.0+ modular agent swarm runtime that transforms complex tasks into executable, graph-structured workflows. It orchestrates multiple specialized agents, tools, and memory systems through a dynamic execution graph, enabling parallel reasoning, structured decomposition, and fully observable workflows. Designed for extensibility and composability, ThreadGraph turns agent-based systems into scalable, reproducible infrastructure rather than linear prompt chains.

Perspective Engine is a modular, human-in-the-loop AI system that transforms trending topics and local signals into original, niche-aligned content perspectives. Instead of generating repetitive or saturated content, it analyzes information across multiple sources, detects overused narratives, and reframes ideas into unique angles tailored to each creator’s audience, location, and industry.

Encrypted reminders, scheduling, tags, SSE, and natural language agent API.

https://demsking.gitlab.io/oremi-isinmi-agent

OntologyRuntime is a semantic runtime system that converts natural language intent into structured, validated, and execution-ready ontologies. It enables users to describe tasks in plain language while automatically generating machine-readable structures for configuration, automation, and AI-driven execution.

No Lock-In Compliance Standard (NLCS v1.0) is an open architecture and governance framework designed to eliminate vendor lock-in across AI systems and software infrastructure. It defines a fully modular, interchangeable system model where AI, data, execution, and policy layers can be independently swapped without breaking system functionality, while maintaining AGPL 3.0+ compliance and machine-verifiable portability standards.

Nexora is an AI-driven enterprise endpoint governance and security intelligence platform that monitors software usage across organizational devices, applies deterministic policy-based risk classification, and transforms raw system activity into structured, auditable insights. It combines endpoint telemetry, policy enforcement, and explain-only AI analysis to give organizations real-time visibility into application behavior, improve compliance, and identify potential security risks without allowing AI to directly control enforcement decisions.

db-gateway-mcp is an MCP server that lets AI coding agents securely interact with MySQL/MariaDB databases across multiple systems and environments—supporting schema inspection, stored procedure discovery, controlled query execution, and future migration automation workflows.

PersonaLock is an open source, identity-first AI platform that preserves a user's authentic voice, reasoning, values, and evidence standards across every interaction. Built around a native identity-aware language model with integrated research and writing capabilities, it archives and learns from user-approved publications while preventing drift through transparent, explainable governance. Instead of simply generating content, PersonaLock ensures every output remains faithful to the person behind it.

A Coinbase x402 micropayment-gated API proxy for The Undesirables TCG Oracle. Allows AI agents to semantically discover and autonomously pay for physical trading card grading and Monte Carlo market intelligence using USDC on the Base network. Fully integrated with the CDP Bazaar Discovery layer.

Production-grade memory operating system for agentic AI. Interoperates with every major framework via MCP, OpenAI-compatible gateway, and native /v1/* REST — Claude Code, OpenClaw, ZeroClaw, Hermes, MemPalace, LangChain, LlamaIndex, CrewAI, AutoGen, Mem0, Letta, Zep. In production use since December 2025. Apache 2.0.

Token operations toolkit — budget, compress, optimize agent context.

AI agent skill for world-class ASCII art. Scenes, UI, 3D, animations — zero dependencies.

API scanning utilities for ChatGPT integrations.

Future AGI experiments — exploring next-generation agent architectures.

Goal-tracking companion for builders. Stay focused, ship more.

Synara platform — agent infrastructure and web tooling.