Hands-on tutorials for building AI agents from scratch. Learn LLM APIs, prompt engineering, tool calling, and the agent loop through practical examples.

Ethicore Engine™ is an AI safety, ethics, and compliance platform. This repo consists of the open-source components of Ethicore Engine™ - Guardian SDK; designed to protect your AI applications from prompt injection, jailbreaks, role hijacking, system-prompt extraction, and 100+ additional threat categories through a multi-layer analysis pipeline

Teleton: Autonomous AI Agent for Telegram & TON Blockchain

Local-first loop engineering for Codex and Claude Code users. Your repo works while you sleep

backlog: Your AI agent forgets between sessions. Backlog remembers.

A lightweight starting point for an agentic coding harness — plus a step-by-step tutorial that walks through how it was built, line by line, with notes on what each piece does and why.

a cli agent tool written in Python + Typescript

App Idea to Final App in one go. Chat the plan, then chill. Build an end to end app straight, Powered By Agentic AI Loops. Agent doesn't stop until Human received their final product.

The open standard and registry for agentic loops: installable, recurring AI agents. One file, any harness.

Language-agnostic best practices for building reliable agentic loops. Pillar-by-pillar guide to goals, persistent state, verification gates, guardrails, and anti-patterns. Zero dependencies.

Run an autonomous company

AI-curated, self-updating directory of MCP servers. Discovered from GitHub & the official registry, analyzed and ranked by AI weekly.

Understanding the agentic ai structure

Self-hosted AI agent gateway — give any local LLM (gemma:2b, llama3) tool calling, RAG, and a full agentic loop. 100% offline. OpenAI + Anthropic compatible.

AI-powered math solver agent with step-by-step reasoning, SymPy symbolic computation, and vision input. 155+ iterations, live at math.heliotrope.online

You're the pilot. Wingman runs the crew. Orchestrate parallel AI agents from a single Claude Code session.

Reusable agentic loop (think/act/observe) template for Claude-powered agents

An autonomous "think-act" loop. A thinker proposes goals; a worker implements them; a committer pushes the results and documents decisions. Repeat.

Token-safe autonomous dev-loop that drives Claude Code (claude -p) through an architect → developer → tester → reviewer → lead cycle to build software from a spec, isolated in a git worktree.

Prompt and command sequencer for light CLI agent automation.