Shipwright Harness

Comparison

How Shipwright compares.

The AI coding-agent field has matured into recognizable tiers. We are not going to pretend the landscape is simple — or that Shipwright occupies a category no one else does. Here is the honest version: where each tool sits, what they are great at, and where Shipwright is genuinely different.

Market structure

The AI coding agent space has settled into three poles. Where you sit on this spectrum should drive which tool you reach for.

Individual Copilots

Cursor, GitHub Copilot

Autocomplete, inline suggestions, single-dev productivity. Excellent at what they do — not designed to coordinate a team's delivery pipeline.

Team AI Workflow Gap← Shipwright

Shipwright Harness

Structured, multi-step delivery with a human review gate, shared task queue, policy controls, and audit trail. The gap between copilot UX and autonomous agents.

Autonomous Agents

Devin, OpenHands, Augment Code

Fire-and-forget agents that operate with minimal human involvement. Best when you trust the agent fully and want maximum autonomy.

Shipwright sits in the middle — team AI workflow — not because individual copilots are weak (they are excellent at developer productivity) and not because autonomous agents are wrong (they are right for the right teams), but because most engineering teams are somewhere in between: they want automation, but with visibility, controls, and a human in the loop on the decisions that matter.

The landscape

Commercial-tier agents in mid-2026 — the tools teams actually evaluate when choosing an AI delivery layer. MIT / own-it / self-hosted is table-stakes on the open-source side — every serious open-source tool runs on your infra, so it earns parity, not separation. The delivery-pipeline layer is already contested: OpenHands runs it today, Augment Code's Remote Agents pull from a background task queue and land review-ready PRs, and the commercial tier is moving fast.

Facts verified as of September 5, 2026, from each vendor's own primary sources (linked in the table below). Re-checked immediately before this page ships — vendor terms change.

ToolLicenseModelsTask QueueTeam VisibilityPolicy ControlsHuman Review GateCron / SchedulingSlack-Native WorkflowTests-First Enforcement
Devin [source] CommercialProprietaryYesDashboardSecurity profiles, network policy, audit logsOptionalYesYes — Slack CodeNo
Cursor [Slack] [automations] [policy controls] CommercialAgnostic (multi)No shared backlogTeam dashboardModel/MCP/repo allowlistsPR review, no plan gateYes — cron and event automationsYes — @cursor launches cloud agentsNo
GitHub Copilot Agent [coding agent] [model selection] CommercialAgnostic (Claude / GPT / Gemini / Grok)Issues-basedPR-levelRepo policiesPR reviewYes — scheduled and event automationsYes — Slack and TeamsNo
OpenHands [enterprise vs OSS] [automations] MITAgnostic (100+)YesDashboard (Agent Canvas)RBAC (commercial)OptionalYesYesNo
Augment Code [source] CommercialAgnostic (Claude/GPT/Gemini)Yes — Remote Agent queueSlack + PRSOC 2 Type II, ISO 42001PR reviewYes — cron, webhook, event triggersYes — Slack as tool and triggerNo
Factory [source] CommercialAgnostic (Claude/GPT/Gemini, BYOK)Yes — MissionsMission ControlSOC 2, ISO 27001, ISO 42001Missions (plan-approval)YesYes — @-mention task delegationNo
Shipwright Harness MITClaude CodeYes — shared, assignableSlack + PR trailPer-repo, per-skillYes — plan approval requiredYes — cron-nativeYes — first-classYes — enforced

The field is converging on the middle. Factory's Missions now approves a plan before its droids execute, and Augment's Remote Agents land review-ready PRs. So the honest question is no longer who has a review gate, it is whose gate is the default and what it enforces. Shipwright approves a plan on every task, not just as an optional add-on, and it is the only tool here that writes tests first and blocks merge until they pass. That combination, not the gate alone, is the whole point.

What actually makes Shipwright different

Three things hold up under a direct comparison. We have retired the ones that did not.

Tests are enforced, not offered

Everyone in this table can generate tests. Nobody else makes passing them the default gate. OpenHands is explicit that running the suite is CI's job, not the agent's. Factory's Missions do run QA against your app as they work and self-correct, but nothing holds the merge on a red suite. Augment generates tests when you ask for them, and Cursor's missing-test PR checks are rules you opt into. Shipwright writes the failing test before the implementation and will not merge without green CI. It is the pipeline's rule, not the agent's discretion.

[OpenHands: QA is CI's job] [Factory Missions] [Augment: Agent use cases] [Cursor: test generation]

An opinionated loop you can take apart

OpenHands gives you primitives and no opinion: you assemble the pipeline yourself. Factory gives you an opinion you cannot open. Shipwright ships the loop already opinionated, then lets you disable phases, override the review principles per repo, and bolt on your own commands and scheduled jobs. Start on rails, then change the rails.

[OpenHands: primitives, not prescriptions] [Factory Missions]

Open throughout, not open core

MIT is table stakes in open source now, so the question is what the license actually covers. In OpenHands, authentication, role-based access control, multi-user organisations and isolated sandboxes sit in the commercial product. In Shipwright, SSO and scoped per-agent access are in the repo you fork. Their open source converts to a paid product exactly when a team needs it. Ours does not.

[OpenHands: Enterprise vs OSS]

On "own-it": running on your own infra is necessary, not sufficient — a local agent can still read secrets and act on your behalf. Shipwright's answer is permission scoping, approval gates, and an auditable review trail, not "your code never leaves your machine" alone.

Run it yourself

Self-host it on your own infrastructure

Shipwright is MIT-licensed, with no managed service in the loop. The plugin runs inside Claude Code; the cloud agent — admin, metrics, and runner — deploys to Docker or to your own Kubernetes cluster with the bundled Helm chart. Your code and the agent that writes it both stay on infrastructure you control.

helm repo add shipwright https://app-vitals.github.io/shipwright
helm install shipwright shipwright/shipwright

One chart packages the admin, metrics, and agent services (plus an optional PostgreSQL). Runs on Minikube, GKE, and EKS.

  • MIT-licensed — fork it, audit every line, run it in your own cluster.
  • No managed service between your repository and the agent.
  • Bring your own Claude Code credentials — nothing routes through an App Vitals service.

Kubernetes deployment guide →

Head to head

Shipwright vs Devin

Devin is the highest-profile autonomous coding agent — a managed commercial service with a strong benchmark track record. Choose Shipwright when you want the full pipeline, deploy stage included, on infrastructure you own and operate; choose Devin when a fully managed service with no infrastructure to run yourself is what you want.

Read the full, sourced Shipwright vs Devin comparison →

Head to head

Shipwright vs OpenHands

OpenHands is the category leader in open-source autonomous agents — MIT, model-agnostic, deployable on your infra, ~86.3k GitHub stars, and it already runs a delivery pipeline (scheduled tasks, triggers, PR review, opening reviewable PRs). It is the closest project to Shipwright on this page: both are MIT, both open real PRs against your repository, and both occupy the same architectural layer — the team delivery pipeline, not the editor. Its Agent Canvas gives that pipeline a dashboard for creating and managing automations, and its ACP support can launch and drive Claude Code, Codex, or Gemini CLI directly as a subprocess agent — so OpenHands can run the very runtime Shipwright is built on. If you want maximum model flexibility and a mature ecosystem today, it is an excellent choice. Here is where the two genuinely differ:

Choose Shipwright when

  • You have already chosen Claude Code and want a pipeline tuned for it, not averaged across providers.
  • You want tests written first and landed with every change, gated by CI, by default.
  • You want a plan a human approves before the agent builds — structured autonomy with a checkpoint.

Choose OpenHands (or the field) when

  • You need BYOK / model-agnostic across many providers, including local models.
  • You want the largest community and the most mature ecosystem available right now.
  • You are not committed to a single runtime and want to keep that optionality — OpenHands' ACP support can even drive Claude Code, Codex, or Gemini CLI as a subprocess agent.
  • You want this same delivery-pipeline layer — OpenHands occupies it too, with Agent Canvas as its dashboard — and prefer its breadth to Shipwright's Claude Code focus.

Read the full, sourced Shipwright vs OpenHands comparison →

Head to head

Shipwright vs Augment Code

Augment Code pairs a context engine built for very large codebases with "Remote Agents" — cloud workers that pull tasks from a queue, run in the background, and land review-ready PRs — plus a Slack app for codebase-aware Q&A. It is well-funded and enterprise-focused, with real autonomous-agent chops. Here is where the two differ:

Choose Shipwright when

  • You want MIT / self-hosted on your own infra, not a managed SaaS with enterprise contracts.
  • You want a human to approve the plan before code is written — not review after the fact on a PR the agent already opened.
  • Tests-first and CI-green are enforced by the pipeline, not left to the agent's judgment.
  • You have committed to Claude Code and want a pipeline tuned for it, not a router averaging across providers.

Choose Augment Code when

  • Your codebase is very large and you want a purpose-built context engine across hundreds of thousands of files.
  • You want a managed service with enterprise security certifications and no self-hosting overhead.
  • Your team already lives in the IDE and Slack, and wants agent access woven into both.
  • Model flexibility across providers matters more than depth on a single runtime.

Head to head

Shipwright vs Factory

Factory is the closest thing to Shipwright by architecture: its Missions flow decomposes an outcome, approves a plan, then runs specialized droids in a Mission Control view. It is a managed, enterprise-hardened platform with compliance certifications and airgapped deployment. Choose Shipwright when you are on Claude Code and want tests-first enforced, plan-approval on every task by default, and an MIT harness you can fork and run yourself.

Read the full Shipwright vs Factory comparison →

Customizability — opinionated by default, malleable by design

Shipwright ships with an opinionated pipeline: plan, build, review, ship, with tests-first enforcement and a human approval gate. That pipeline is not locked in — every stage is customizable.

Swap skills

Each pipeline stage is a skill. You can replace the default planning skill with your own, add a pre-deploy gate, or swap the review skill for a custom policy check. Skills are plain markdown files — no special build step.

Disable default crons

The built-in review and patch loops ship disabled on new agents. Enable what you want; skip what you do not. Some teams run only the task queue and plan gate, and manage review manually. That is a valid configuration.

Add custom gates

Pre-check scripts can block a cron from firing based on any condition you define — CI status, PR state, time of day, external API call. The gate runs before the agent, so you control when automation is appropriate.

Every tool in the landscape above has converged on some form of this — Devin has Playbooks and CLI-beta Skills, Cursor has rules and hooks, Copilot Agent has custom .agent.md agents, Augment Code has Rules and CLI-only Subagents, and OpenHands has Skills and hooks in the open. The difference is where it lives: for the commercial tools, the deeper extensibility (subagents, hooks, plugins) sits in a separate CLI product, often beta, sometimes pulled without notice (Cursor removed Custom Modes in v2.1). Shipwright's skills, gates, and cron controls are first-class in the one product you actually run.

Honest note: Shipwright is not as easy to customize as rolling your own pipeline from scratch — if you want total control from day one, a bespoke setup is simpler. What Shipwright offers instead is a battle-tested pipeline you can start with immediately, and customize over time as you learn what your team actually needs. Some teams have disabled all the defaults and built their own workflow on top. You own the infrastructure either way.

The honest trade-off

Shipwright runs on Claude Code only. That is a deliberate bet, not an oversight: we think a pipeline built for one excellent runtime beats one hedged across a dozen. If model-agnosticism is a hard requirement, the field above is strong — use it. If you are building on Claude Code and want structure, tests, and a review gate around it, that is exactly what Shipwright is for.

We hold ourselves to the same honesty here: Claude Code is not a closed, locked-in dead end, and we do not pitch it that way. The case for Shipwright is Claude Code quality, not Claude Code exclusivity.

Try it

Install the plugin into Claude Code and run a task end to end. Free, MIT, runs on your own infra.

/plugin install shipwright@app-vitals/shipwright