Ralphy runs on your machine and coordinates coding assistants as they work through a task list. It's for developers who want to hand off a feature request or product requirements document rather than prompt an agent for each individual task. It handles single requests too.
The command-line tool runs on macOS, Windows and Linux. It requires an existing AI coding CLI, with support for Claude Code, Codex, OpenCode, Cursor agent, Qwen-Code, Factory Droid, GitHub Copilot and Gemini CLI. You can choose the model through the selected engine. Ralphy manages the local workflow; the engine handles AI requests.
Tasks can come from Markdown, YAML, JSON or GitHub Issues. For larger projects, it combines tasks across a folder of Markdown files and records completion in the corresponding file. Project rules apply across tasks, including coding conventions and boundaries around files agents shouldn't change.
Parallel execution gives agents separate Git worktrees and branches. You can keep their work on separate branches, create pull requests, or let Ralphy merge changes with AI assistance for conflicts. Task groups control which work runs together and which waits for earlier tasks. A lighter sandbox mode avoids duplicating large dependency directories.
Ralphy can run tests and lint checks during the coding workflow. Its agent-browser integration lets agents check interfaces and test forms in a browser, while Discord, Slack and custom webhooks can report session completion and failures.
Claim this page and we'll verify you by hand. Ralphy gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Ralphy?Promote it
Something wrong or outdated on this page?
106Updated 2 weeks ago
macOS · Windows · Linux · Web#Agent Skills#Code execution#Git integration
Albert coordinates Claude Code agents for developers who want to hand off a coding goal across several tasks. Its harness and dashboard run locally on Windows, macOS or Linux, and it requires an installed, signed-in Claude Code account. It assigns work to Haiku, Sonnet or Opus according to the task and continues until the goal is complete or it reaches a requested review checkpoint.
42Updated 2 days ago
macOS · Windows · Linux · Docker#Agent Skills#Code execution#Distributed execution
41KUpdated 17 hours agoMIT
macOS · Windows · Linux · Android · Docker · Web#Agent Skills#Code execution#Human approval
127.4KUpdated 17 hours agoApache-2.0
macOS · Windows · Linux#Code execution#Git integration#Human approval
322Updated 3 weeks agoMIT
macOS · Windows · Linux#Agent Skills#Code execution#Human approval
4.4KUpdated 1 day agoMIT
macOS · Windows · Linux · Web · JetBrains#Agent Client Protocol#Code execution#Git integration
Code Buddy is an AI coding assistant for developers who want a terminal agent running on their own machine, with a choice of local or cloud models. It reads repositories, edits code and runs commands on Linux, macOS and Windows. Ollama keeps model inference local without an API key or account; cloud providers send model requests off the machine. Routing includes automatic provider failover.
Codewhale is a coding agent that runs on your computer and works with a model you choose. It's for developers who want help understanding a project, fixing bugs or automating repeated work, with control over the agent's access to files and commands. The open-source project uses the MIT license and is written in Rust.
Codex CLI is an open source coding assistant that runs on your computer and works with local repositories. It's for developers who want to explore code, make changes, and use their existing development tools from the terminal. It runs on macOS, Windows, and Linux under the Apache 2.0 license.
Devo is an MIT-licensed, open-source coding agent for developers and teams who want a local workspace with their choice of model provider. It has a desktop app and a terminal interface, with support for macOS, Linux, Windows and Kylin OS. Its compact Rust runtime runs as a single binary without runtime dependencies.
gptme is a self-hosted AI agent that works directly in your terminal, with access to your files and installed tools. It's for developers who want a coding assistant in their own environment, and people who want an agent for data analysis or other knowledge work. The software is free under the MIT license and doesn't require a gptme account.