Crewplane is an open-source orchestration harness and CLI framework developed by the crewplaneai team, designed to coordinate and execute structured multi-step AI coding workflows against local codebases. It serves as an execution plane that orchestrates agent invokers, manages isolated git worktrees, captures structured execution artifacts, and enforces automated review loops. In day-to-day operation, Crewplane is executed from the terminal to run defined developer workflows and skills. It utilizes typed provider adapters to interact with backend models and agent processes while isolating task executions in dedicated git worktrees. This architecture ensures that code edits, testing routines, and multi-stage refinement loops occur in isolated workspace contracts, generating observable logs and diff snapshots throughout the run. What distinguishes Crewplane from basic interactive coding assistants is its focus on harness orchestration, process isolation, and workspace boundary management. Rather than operating as a simple one-off chat assistant, it manages provider lifecycles, reaps zombie processes, enforces snapshot validation, and captures artifacts across distinct workflow stages. Crewplane is distributed as open-source software under active development on GitHub, with packaging support for standard package ecosystems including Homebrew and Python environments.
Git Worktree Isolation — Executes coding tasks and agent workflows in isolated git worktrees to prevent dirty states and uncommitted changes on main branches. - Automated Review Loops — Enforces iterative review-and-fix cycles to validate, test, and refine agent-generated patches before integration. - Typed Provider Adapters — Utilizes strict typed interface contracts and invoker helpers to manage subprocess execution and backend provider lifecycles. - Artifact & Observability Tracking — Captures task snapshots, execution logs, and workflow outputs into structured artifacts for auditing and debugging. - Modular Workflow Skills — Supports modular, declarative workflow definitions and skills to standardize repeatable terminal tasks.
Use cases
Use Case: Isolated Code Generation and Refactoring A developer dispatches an automated refactoring or feature implementation task via the CLI. Crewplane spawns an isolated git worktree, executes the invoker agent, captures the patch diff as a verifiable artifact, and facilitates safe review without interrupting local editor state.
Use Case: Automated Multi-Agent Review Pipelines An engineer configures a multi-stage review workflow where generated code is automatically subjected to linting checks, type verification, and secondary reviewer agents. Crewplane orchestrates the review-loop until typed validation passes.
Use Case: Headless CI/CD Automation Workflows Teams integrate Crewplane into terminal scripts and automation pipelines to execute automated bug-hunting, documentation generation, or migration skills headlessly with robust provider process lifecycle management.
Who it is for
Crewplane is built for software engineers, DevOps developers, and platform teams building structured multi-agent coding workflows that require git worktree isolation and strict artifact tracking. It is not intended for users seeking a lightweight, purely GUI-based chat extension for IDEs.
Install guide
Installation Install Crewplane via Homebrew or standard Python package tooling: bash # Via Homebrew brew install crewplaneai/tap/crewplane # Or via pip pip install crewplane
First Run Ensure required provider API credentials are set in your shell environment and verify the CLI installation: bash # Export provider API keys export ANTHROPIC_API_KEY="your-api-key" export OPENAI_API_KEY="your-api-key" # Check CLI status crewplane --help
Example Session Execute a workflow skill in an isolated worktree: bash # Run a workflow skill against your codebase crewplane run --skill create-workflows --prompt "Refactor auth router to use typed request validation" # Inspect run status and generated artifacts crewplane status
SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
Vibe Kanban — Vibe Kanban, originally developed by Bloop AI, is an open-source orchestration harness and visual task board designed to manage and…
Parallel Harness Pets — Parallel Harness Pets (parallel-harness-pets) is an open-source companion tool and harness plugin created by TevvvB. It is designed for developers…