Codex Loop

A control loop that turns Codex subagents into a continuously refilled engineering team—with isolated workers, independent model review, headless scale, and a live dashboard.

Improve how you work with AI. Portable Claude Code and Codex skill with evidence-based assessment and evaluation.

AI coding agent with one Python core and three front-ends — headless CLI, Textual TUI, and an Electron desktop. Works with any OpenAI-compatible API, with risk-tiered permissions, event-sourced replayable sessions, and a fail-closed OS-level sandbox.

Privacy-first AI project and Skill feedback loop for Codex and Claude Code—turn corrections into traceable requirements and verified repair plans.

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-agent backends through an MCP server + CLI.

Composable Agent Skills (Claude + OpenAI Codex) for taking an idea from fuzzy → validated → sequenced build → shipped — a manual tier (ideate, deep-dive, prompt-pack) and an autonomous tier (autopilot, build-loop).

SRT 驱动的双后端 B-roll Agent Skill：自动路由 HyperFrames / Remotion，集成 152 张 Shotcraft 镜头卡

Agent skills for bespoke websites and app UI: product-derived direction, no generic AI templates, and a Playwright screenshot review loop. Installs into Claude Code, Codex, Cursor, Copilot, Gemini and more via npx.

Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.

Claude orchestrates and reviews; Codex CLI implements. A Claude Code plugin for the two-model kitchen: /serve tasks end to end, /simmer goals until green. Your head chef doesn't chop onions.

Multi-modal voice agent for your AI agents. Talk with Claude Code, Codex, and others by voice: answer their prompts, give instructions, ask what they did. Or just nod.

Smithers is an agentic workflow framework for defining workflows in simple TypeScript configuration files and executing them quickly, durably, and reliably

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok — multi-task ledger loop (related or not), host-portable (re-send the prompt to continue), clean-context supervisor, verified gates. Markdown library (loop-graph · quest), not a framework.

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

Deterministic orchestrator for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). No model in the coordination loop, so parallel runs in per-task git worktrees replay byte-identically. Signed lineage plus an opt-in HMAC audit chain a reviewer checks offline, without rerunning it. Cluster mode, air-gap deploy. https://bernstein.run

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

The best way to get AI coding agents to solve hard problems in complex codebases.

The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever.

A self-hosted workspace where people and coding agents work together across projects, sessions, and providers.

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

Better 'AskUserQuestion' - A lightweight MCP server/OpenCode plugin/Agent Skills + CLI interface which allows parallel AI agents ask questions to you. Be the human in the human-in-the-loop!

Art and animation, written as code. Illustrations, loops, interactive web art, launch-videos and scored films in dozens of styles, identical on every render.

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.