Your autonomous engineering team in a CLI. The agent loop produces senior-level code that you can actually trust in prod because of non-negotiable feedback from independent reviewers. Supports Claude Code, OpenAI Codex, OpenCode, and Gemini CLI with trivial setup.

Design visual, review-gated agent loops for Claude Code before you run them.

File-based kanban board for autonomous agentic loop. CLI and TUI for multi-agent workflows. Skills included.

OpenCode plugin: Ralph outer loop + RLM inner loop — iterative AI development with file-first discipline and sub-agent support

Personal AI agent — tell it what you want, it figures out how. Runs locally, plans autonomously, writes code, browses the web, and gets things done.

An agent-native setup kit for turning a well-scoped repo into a supervised multi-agent coding loop, with Beacon loop planning. Stop prompting coding agents one task at a time. Give your repo a loop.

Documentation control room for the era of AI agent loops

AI coding assistant built for real developer workflows.

Reusable playbooks for autonomous AI agent loops — copy, customize, ship.

Open RDelta/Babel Index framework for LLM agents and world-systems: detect context degeneration, agent loops, tool fragility, and collapse with NEOTH.

Loops, not prompts. A curated list of loop engineering patterns, tools and templates for AI coding agents.

Standardized AI Looping Language

Runnable, bounded AI-agent loops — an independent gate verifies every lap under nine enforced safety bounds plus a kill switch. The runnable engine layer for loop engineering. 63 runnable loops across a dozen industries, keyless.

Universal DSL and runtime for agent loop engineering — portable AI agent loops across LangChain, LangGraph, CrewAI, AutoGen, and OpenAI

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.

Agent loop patterns and reusable Codex queue-loop template

Always-on agentic dev harness that watches your GitHub issues and triages, plans, implements, reviews, and opens PRs on its own — with a live Mission Control dashboard. Elixir/Phoenix, driven by Claude.

A closed agent loop you can verify — runs in an EigenCompute TEE, signs every result, verified in your browser

Predefined, reusable agent loops for Pi — declarative YAML pipelines with review gates, scoring, and goal-loop convergence. Built on pi-subagents.