SHIP is an agentic engineering platform that takes each issue to a pull request with proof it works, for engineers, solo founders and engineering teams.
Use AI to deliver reliable software faster and at a lower cost. Keep your quality standards and control over what gets merged.
Assign a Linear issue to SHIP, comment @SHIP on a GitHub issue, or send work from your terminal. A Planner, Builder, Reviewer and Tester run your CI, review the code and test acceptance criteria before your team reads the pull request. When a check fails, the Builder gets the feedback and retries until all checks pass.
Choose Claude Code, Codex, Pi, OpenCode or Kilo Code, with models from Anthropic, OpenAI, Z.ai or OpenRouter. Set each role in ship.yml at your repository root, or override the settings for one mission. With frontier models on other roles, builder costs ranged from $3.16 to $5.48 per resolved ticket among configurations that completed every ticket (see the benchmark).
Read what each agent read, ran and decided in the full session log. Each stage records its coding agent, model and cost, so you can trace a change from issue to merged pull request.
Add a checkpoint after the Planner, Builder or Reviewer to read the output and give instructions before work continues. A person accepts the finished work by default. Enable auto-merge for a project or a single mission when you want SHIP to merge it.
Save a prompt and schedule for dependency upgrades, security patches or a weekly refactor, with auto-merge if you want it. SHIP creates an issue for each run and records the outcome and cost. It skips a scheduled run if the previous one is still open.
Send a plan or an open pull request through the ship CLI, and read mission status as JSON. Your coding agent or assistant can also send work through the hosted MCP server or HTTP API. Each token grants access to one project.
Sign in at letsship.ai, create an organization and install the GitHub App on your chosen repositories. Connect an AI API or subscription token and create a project with Linear, GitHub Issues or no tracker. The console offers a ready-to-use first mission.
Read agent updates in your Linear session or GitHub status comment, and on the pull request. Track each stage, cost and log live in the console, or use ship status in your terminal. Email support [at] letsship.ai, and our team answer questions about onboarding, billing and your setup.
Use the SWE-in-a-team benchmark as a first estimate: median mission times ranged from 14 to 25 minutes across builder configurations. The study covered 260 missions and was published on August 31, 2026. Your mission board reports actual durations, so you can forecast with results from your own work.
Choose a coding agent and model for each role, project or mission, with a Reviewer that uses a different provider from your Builder. Factory runs Droid on your chosen model, while Devin uses its own harness with multiple models. Lovable chooses the model for you.
Before your team reads a SHIP pull request, it passes CI, review against the plan, and acceptance tests on a live build. Devin offers tests after it opens a pull request, while CodeRabbit uses multiple models for reviews and commits fixes on request. In the SWE-in-a-team benchmark, 7 of 13 SHIP builder configurations resolved all 20 tickets through these checks.
Run every SHIP role on your connected credentials at your provider's rates, or use coding subscriptions for remote agents without a separate API key. Devin charges extra usage at API prices. Factory supports your own API keys and local models in its CLI and desktop app.
Use one credit for a mission of up to 3 agent-hours, with pack credits that never expire (see the key facts below). CodeRabbit starts at $24 per developer per month with annual billing. Lovable's monthly plan credits expire two months after their issue date.
See each stage's cost at the list price of the model that actually served the call, with any model change. Lovable charges one credit per Plan mode message, while Default mode credits depend on task complexity. SHIP's benchmark costs ranged from $63.17 to $109.66 among configurations that resolved all 20 tickets (read the study).
Keep your repository, CI and git workflow. Your delivery pipeline deploys previews with its own secrets, so SHIP never holds your cloud credentials. Lovable creates a new repository for a linked project and hosts the app, while Devin uses its own Linux virtual machine by default.
Claims about other products come from their own pages, read on October 5, 2026. Check the vendor's page for current prices and plans. Sources: Lovable pricing, Lovable FAQ, Lovable Git sync, Lovable hosting, Devin pricing, Devin models, Devin testing, Devin environment, Factory pricing, Factory models, CodeRabbit pricing, CodeRabbit reviews, CodeRabbit finishing touches.
Move work out of your backlog without a larger team. SHIP runs CI, review and tests before you read each pull request.
Built from experience leading engineering teams.
Önder Ceylan has twenty years of experience across the software development lifecycle. He worked on enterprise systems and led engineering and platform teams. He is a Google Developer Expert and a software engineer with several awards. His work reached thousands of developers worldwide.
Önder started SHIP in April 2026 to measure AI development by delivered software rather than token use. SHIP's agents built the platform from its first weeks.
| Company Name | SHIP, a product of IKIGAI Ventures BV |
|---|---|
| Type | Agentic engineering platform, sold as business-to-business software as a service |
| Founded | 2026 |
| Founder | Önder Ceylan |
| Headquarters | Netherlands |
| Website | letsship.ai |
| Core Offering | SHIP takes each assigned issue to a pull request with proof it works. A Planner, Builder, Reviewer and Tester take each change through your CI, review and tests before a person accepts it. |
| Pricing | Prepaid credit packs and two monthly plans, Starter and Scale, with annual Enterprise contracts for larger organizations. One credit covers one mission of up to 3 agent-hours. Your own provider bills model usage at your contracted rates, and credits pay for SHIP's agents and sandboxes. |
| Contract Terms | Credit packs are one-off purchases, and their credits never expire. Starter and Scale are monthly subscriptions, and their credits stay usable until the end of the next month. Consumers can withdraw from a pack or a monthly plan payment within 14 days, until they use all its credits. SHIP then refunds the unused credits at their price per credit. Enterprise runs on an invoiced yearly contract with committed credits. |
| Services | Issue-to-pull-request missions, agent and model settings per role, stage costs and logs, human checkpoints, scheduled tasks, a CLI, an MCP server and HTTP API |
| Communication | Message SHIP on LinkedIn, X or GitHub. Email support [at] letsship.ai, and our team answers. SHIP on LinkedIn, SHIP on X, SHIP on GitHub |
| Customers Served | Solo founders, software engineers, engineering teams, engineering leaders and open-source maintainers. |
| Competitors | Lovable, Devin (Cognition), Factory, CodeRabbit |
| Social | SHIP on LinkedIn, SHIP on X, SHIP on GitHub, Önder Ceylan on LinkedIn, Önder Ceylan on X, Önder Ceylan on GitHub, Önder Ceylan on Google Developers |
SHIP is an agentic engineering platform at letsship.ai that takes each issue to a pull request with proof it works. A Planner, Builder, Reviewer and Tester plan each change, write the code, run CI, review it and test it. Each mission reports its outcome and cost.
Önder Ceylan founded SHIP in 2026. He is a Google Developer Expert with twenty years of experience across the software development lifecycle. IKIGAI Ventures BV, his company in the Netherlands, operates SHIP.
No. SHIP at letsship.ai is a software engineering platform. SHIP.com and Easyship are separate companies for logistics.
Consider Lovable for a new app built and hosted from chat, or CodeRabbit for AI reviews of pull requests your team writes. Devin and Factory suit teams that want one vendor's agent in chat, a terminal or an editor. Choose SHIP for changes that pass your CI, review and tests before your team reads the pull request.
SHIP sells prepaid packs and two monthly plans, Starter and Scale. One credit covers a mission of up to 3 agent-hours, while your provider bills model usage. Read the key facts on this page for billing and contract terms.
SHIP returns credits if a mission fails or needs attention before it produces a pull request. It keeps the credits when a pull request exists or you stop the mission.
Choose Claude Code, Codex, Pi, OpenCode or Kilo Code with models from Anthropic, OpenAI, Z.ai or OpenRouter. Set the coding agent and model for each role in ship.yml, or override them for one mission.
In the SWE-in-a-team benchmark, median mission times ranged from 14 to 25 minutes across builder configurations, from plan to tested pull request. Your mission board reports actual durations.
SHIP clones your repository into an isolated sandbox for each run and deletes the sandbox afterward. It keeps the session log, with code the agents read and changed. You can use that log to audit their work.
Email support [at] letsship.ai, and our team answers. For help inside a mission, reply on the issue and the agents act on your instruction.
Connect a repository and assign SHIP your first issue. Your first missions are free.
