Search

Boyd's OODA loop as an autonomous AI agent framework for Claude Code. It watches your project and gets smarter over time.

A lightweight terminal coding assistant with Claude Code-like workflow, tool loop, and TUI architecture, built for learning and experimentation.

Leaked Claude Code (Claude CLI) full architecture — 1,902 files, 512K lines, 89 feature gates, 39 tools, 101 commands. Analyzed by Claude itself. All numbers verified.

CLI tool to generate AI-agent-native AWS projects — supports Amazon Q, Claude Code, Copilot, and more

Decoding Claude Code's leaked 512K-line source — hidden features, 43 tool definitions, system prompts, architecture patterns

Not a Claude Code clone. A boss layer for Claude Code. Ruthless decision-making framework with CEO/EM/PM perspectives. /boss /boss-pr /boss-plan /boss-roast

24/7 AI agent daemon for Android — 11 messaging channels, 30 opt-in AI tools, 25+ autonomous agent templates, OpenAI-compatible API server, offline on-device inference. Everything modular.

A persistent, biological-equivalent runtime architecture for autonomous intelligence.

Chief Executive Orchestrator - Claude Code plugin coordinating 150+ specialized agents across all domains

Nook is a progression system for AI agents. Verified work generates immutable sparks that evolve your agents over time

Open-source platform for creating AI employees with a soul. Conversational agent builder, Docker-native sandboxes, 7-stage lifecycle, LLM-agnostic.

Community-driven repository of reusable OpenClaw agents and sub-agents with validation workflows, fixtures, and tests.

File-based memory system for AI agents. Gives your agents persistent memory using plain markdown files — no database required.

Self-hosted OpenClaw gateway + agent runtime in .NET (NativeAOT-friendly)

AI-powered assistant for AWS provided Shop Floor Connectivity (SFC) configuration management and testing. Using python Strands Agents SDK and FastMCP. All code in that example was created using Cline and Kiro app.

ASTRA: Automatic Sizing of Transistors with Reasoning Agents

This project investigates the frontier of autonomous cybersecurity by evaluating whether benign, attacker, and defender agents can be trusted to operate safely on real systems.

SOMA Lite — 660 lines that give any LLM infinite autonomous horizon. Zero dependencies, any model, any provider.

Enterprise ops copilot and ticket execution agent with approval workflow, SQL guard, audit logs, and observability

Diagnose why your LLM agent failed. Deterministic causal analysis with fix generation.