Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
A Personal AI Assistant that lives inside your machine and works 24/7 for you.
Mathematical benchmark exposing the massive performance gap between real agents and LLM wrappers. Rigorous multi-dimensional evaluation with statistical validation (95% CI, Cohen's h) and reproducible methodology. Separates architectural theater from real systems through stress testing, network resilience, and failure analysis.
The Architecture Review Agent is an open-source AI agent sample that reviews software architectures and generates interactive diagrams automatically.
🎙️ Voice-native document intelligence using Gemini, ElevenLabs STT/TTS, and Datadog observability — turning text documents into spoken conversations.
Build production-ready AI agents in Claude Code from natural language. Analyzes your problem, researches best practices, and generates subagents, skills, hooks, commands & MCP configs.
A Recursive Ontological Framework for Cognitive Design, Neurodivergence Modeling, AI Co-Development, and "Structural AI"
Technical Research: System prompts as governance constitutions for AI developer assistants.
Benchmarked agent execution runtime for Python. Sub-10ms cold starts, real-time streaming, time-travel debugging, and self-growing tool libraries. Compare 3 sandbox backends: Docker (OpenSandbox), MicroVM, and in-process AST.
Deterministic architecture for multi-agent observability, verification and controlled degradation.
Transform your AI from a forgetful junior dev into a Senior Tech Lead. Persistent project memory + specialized agent skills for any AI coding assistant.
Embodied agent that learns from human teaching; hybrid agent architecture with computer vision, AI planning, knowledge graph reasoning & generalization , inverse kinematics. Supported by the DARPA GAILA program.
Real-world patterns for shipping AI agents to production. Learn versioning, cost optimization, multi-tenancy, guardrails, and observability through runnable TypeScript examples.
Case Study of the laboratory plant myJoghurt - implemented with JaCaMo BDI agents embedding an engine for processing the NPL(s) language and a set of capabilities for approaching the sanctioning norm enforcement process
OpenClaw source code architecture analysis of a production AI Agent gateway — Agent Loop, memory, tool sandbox, custom WebSocket protocol, 20+ IM adapters. 从 Agent Loop、记忆系统、工具沙箱到自研 WebSocket 协议 —— 拆解一个真正跑在生产环境中的多通道 AI Agent 网关是如何设计与实现的。
LIFE — Persistent identity architecture for AI agents. 16 MCP servers: drives, heart, memory, patterns, journal, genesis, garden, vision, voice, and more. Zero dependencies. Built across 938 conversations.
Comprehensive cognitive infrastructure for AI-augmented development and knowledge work
A comprehensive reference for building and organizing AI agent skills across Claude Code, KiloCode, OpenClaw, and OpenAI Codex. Covers SKILL.md specifications, folder structures, mode-scoped skills, agent orchestration, and self-hosted model configuration.
A lightweight, pluggable memory backend for agent-based simulations. Supports temporal data, experience replay, and persistent state logging
Emotion Vector Memory (EVM) v2.1 — Model-agnostic identity continuity and directed vector interaction standard for long-term AI systems.
Add a description, image, and links to the agent-architecture topic page so that developers can more easily learn about it.
To associate your repository with the agent-architecture topic, visit your repo's landing page and select "manage topics."