A

agent

Agent-shape testing harness that measures how an LLM-driven agent uses a tool's CLI, scored by an LLM judge.

This repository provides an offline AI-Agent Terminal that integrates Retrieval-Augmented Generation (RAG), Planner-Builder and Agents IA with locally hosted distilled language models by OLLAMA, GPU-accelerated embedding and generation, rotating logs, and an interactive console workflow.

Composable Agent primitives for Kit applications

The core Swytchcode Execution Kernel for AI Agents & Developers.

A living memory system for the AI agent(s) that assist your daily work. Supported by ChatGPT, Claude, V0 and many others. Get started in 5 minutes with our managed service, or clone the repo and host completely free.

My opinionated Claude Code config. No—I do not vibe code nor will I ever pay for these services, however some clients provide access and request that I work with it.

Ruby gem providing RubyGems and Ruby version information via MCP (Model Context Protocol) server tools. Integrates with MCP-compatible clients like Cursor IDE, Claude Desktop, and other MCP-enabled tools.

Personal PI agent harness.

Framework for building LLM-based agents

🧠 Open-source persistent memory engine for AI agents and LLMs with semantic search, automatic deduplication, and intelligent context retrieval.

A comprehensive climate agent for weather forecasts, geocoding, and pollen data. https://demsking.gitlab.io/oremi-weather-agent

Personal skills and agent configuration

Agentics provides a complete AI infrastructure ecosystem covering every aspect of building modern AI-powered applications

from language model inference across 27+ models, to voice processing with TTS/STT/VAD/EOT, semantic embeddings, secure networking with tunnels and VPN, real-time financial data streaming, and comprehensive developer tools including CLI and mobile apps.

The modular architecture allows businesses to use individual components or the entire suite, with production-ready deployment, monitoring, and South African payment integration. Whether you're building a voice assistant, an AI-powered application, or need secure infrastructure for remote access and real-time data, Agentics provides the complete toolkit

🤖 BugZero AI: The Story of Autonomous DevOps 🌌 The Inspiration: Closing the "Window of Exposure" In the current landscape of rapid-fire deployments, the interval between a developer pushing a code change and a security team discovering a leaked credential or a critical bug is often the most dangerous time in a project's lifecycle. We call this the Window of Exposure.

During this window, an exposed OpenAI key or AWS credential can be sniffed and exploited by bots in under 60 seconds. We were inspired by the concept of "Zero-Mean-Time-to-Fix"—the idea that the moment a vulnerability exists, the fix should already be in progress. BugZero AI was born to be that "invisible pair programmer" who never sleeps, ensuring that for every bug introduced, the remediation starts at t = 0

Bash wrapper for Hermes Agent and LXC