frankbria/ralph-claude-code Alternatives

pick it when you want the same Ralph loop as a single Rust binary with stricter orchestration instead of a bash script around the Claude CLI

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

choose it when the same loop must also drive OpenCode, Codex or Copilot, not just Claude Code

Type `ralph "prompt"` to start open code in a ralph loop. Also supports a prompt file & status check. Open Code, Claude Code, Codex, Copilot

choose when you want plan-file-driven execution that deploys as one Go binary with no Node or shell toolchain

Extended Ralph loop for autonomous AI-driven plan execution

choose when every loop iteration should land as a PR gated on CI instead of editing your local working tree

🔂 Ralph loop with PRs: Run Claude Code in a continuous loop, autonomously creating PRs, waiting for checks, and merging

choose when you want a visual/hosted general task-agent platform instead of a CLI loop that only drives Claude Code

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

choose when you want an agent with its own sandboxed runtime and web UI rather than shelling out to Claude Code

🙌 OpenHands: AI-Driven Development

choose when you want deterministic, versioned coding workflows in TypeScript instead of an unguided prompt loop

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

choose if you want long-running coding tasks managed by a self-improving TypeScript agent rather than an external shell loop

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

choose for large multi-file projects needing built-in context management, but note ~12 months without a push

Open source AI coding agent. Designed for large projects and real world tasks.

choose for multi-agent production orchestration in Python, at the cost of a much heavier runtime than a shell wrapper

Multi-Agent Harness for Production AI

choose if you'd rather have a self-contained Python terminal agent with its own tools and no Claude Code dependency

Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

choose only if you need to build custom agent cognition in Python (GPL-3.0) rather than use an off-the-shelf loop

Extensible AGI Framework

choose for a self-hosted multi-agent runtime with 23+ LLM providers when you don't want to be tied to Claude Code

Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.

choose for a local-first agent OS with workflows and scheduled goals instead of a single prompt loop

The local-first operating system for building, running, and improving AI agents, workflows, and autonomous goals.

choose when you want to swap Claude Code, Codex and Cursor harnesses under one policy and sandboxing layer

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

a single-author bash setup with no license and no rate-limit or exit guards — fine for personal use, risky as a dependency

My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & Droid in a loop until your PRD is complete.