Galley

Galley is an open-source agent orchestrator and task execution harness developed by shinpr. Implemented primarily in Go, Galley coordinates AI coding tasks through dedicated background daemon workflows, structured task schemas, and plugin-based agent interfaces. In practical usage, Galley acts as an execution engine that manages task handoffs, revision lifecycles, and agent execution across environments. It provides explicit plugin support for agent ecosystems like Claude and Grok (via dedicated plugin manifests such as `.claude-plugin` and `.grok-plugin`), allowing external AI models to interact with local repository workflows, run tasks under predefined execution timeouts, and track execution state. Galley distinguishes itself by focusing on daemon-driven background execution and structured executor recovery skills rather than being a standalone interactive chatbot. Its architecture emphasizes task handoffs, modular prompt configurations, and schema-validated inputs to maintain reliable agent execution across long-running development jobs. Galley is distributed as open-source software on GitHub under active repository development with native Go tooling.

Tags: ai agent, cli, code assistant, coding agent, developer tools, OpenSource

Visit Galley

Key features

• Daemon-driven task orchestration — Runs coding agents and subtasks through a structured background daemon workflow. - Agent plugin integrations — Provides dedicated integrations and manifest support for environments like Claude (.claude-plugin) and Grok (.grok-plugin). - Task handoff and revision management — Handles formal task transitions, revisions, and state tracking across execution phases. - Executor recovery skill helpers — Built-in recovery routines to gracefully handle and resume failed agent executions. - Configurable task timeouts — Supports baseline and extended execution timeouts suited for long-running batch development tasks. - Schema-validated execution — Enforces structured task schemas and prompt templates to standardize agent inputs and outputs.

Use cases

Use Case: Orchestrating Long-Running Agent Tasks Developers can run Galley as a background daemon to execute multi-step code generation and refactoring pipelines without blocking the primary interactive terminal. Tasks run against predefined timeouts and schema constraints to ensure reliable completion.

Use Case: Managing Agent Handoffs and Revisions Teams can structure complex coding workflows where tasks are drafted, executed, and handed off across multiple plugin environments like Claude or Grok. Galley tracks task status and manages revisions systematically.

Use Case: Automated Failure Recovery in CI and Batch Jobs Engineers can leverage Galley's executor recovery helpers to automate error handling during agent-driven code execution, reducing the need for manual intervention when subtasks fail.

Who it is for

Galley is designed for software engineers and systems developers who need a Go-based orchestration harness to manage multi-step, daemon-driven AI coding tasks across agent ecosystems like Claude and Grok. It is less suitable for users looking for a plug-and-play interactive TUI chat assistant.

Install guide

Installation Galley is written in Go and can be built from source using standard Go tooling: bash git clone https://github.com/shinpr/galley.git cd galley go build -o galley ./cmd/galley sudo mv galley /usr/local/bin/

First Run Ensure your local environment is configured with any required agent API credentials or plugin configs, then inspect the CLI options: bash galley --help

Example Session To start the Galley daemon and execute a schema-defined task workflow: bash # Start the Galley daemon galley daemon start # Dispatch a task using a project schema and prompt configuration galley task run --schema ./schemas/task.json --prompt ./prompts/refactor.md

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

• Plandex — Plandex is an open-source terminal-based AI coding agent designed to handle complex, multi-file engineering tasks in large codebases. Created by…
• OpenCode — OpenCode is an open-source AI coding agent developed by Anomaly that operates across terminal environments, desktop applications, and IDE extensions.…
• OpenHands — OpenHands (formerly OpenDevin) is an open-source autonomous AI software development agent and orchestration platform. It provides an extensible runtime environment…
• Subtask — Subtask is an open-source CLI agent harness and orchestration tool developed by zippoxer in Go. It is built to coordinate…
• EchoCoding — EchoCoding is an open-source agent harness and audio-augmented developer tooling layer created by launsion-boop. Designed to run alongside AI coding…
• pi-reflect — pi-reflect is an open-source agent harness and self-improvement extension for pi coding agents, developed by jo-inc. It inspects agent session…