agentic-loop

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

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

a cli agent tool written in Python + Typescript

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

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

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

Understanding the agentic ai structure

An observable local Agent loop with controlled tools, permission gates, trace viewing, and history replay.

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.

Agentic loop that tasks 3 llm's with agreeing on the best response to a user prompt

A local-first AI agent powered by Ollama that connects to a remote SpendWise MCP server. Features a custom Python agentic loop with schema-aware argument repair to fix LLM tool-calling hallucinations.

Multi-tiered loop-until-done task execution toolkit: CLI, Claude Code skill, MCP server (Python + TypeScript), and orchestrator client with circuit breaker.

An Agentic Loop framework using CrewAI that automatically writes, executes, tests, and fixes Python code errors without human intervention.

A self-extending agent harness: on hitting a capability gap the agent authors a new tool plus a test, verifies it in a sandbox, and promotes it only on a pass

The automation and the people advance in lockstep.

Simple autonomous claude code loop with ensemble quality control

A pytest-based API testing framework for the TMDB REST API, showcasing modern SDET: end-to-end integration tests, Pact contract validation, Dockerized parallel runs, Kubernetes-based local runs, GitHub Actions CI/CD, AI-powered test-failure diagnosis, and an LLM Judge evaluation framework that scores diagnosis quality. An MCP server for AI agents.