# Devin alternatives in 2026, compared on their own docs

> Codex, Copilot cloud agent, Cursor, Factory, Warp, Tembo, OpenHands and SHIP compared with Devin on triggers, models, checks and price.

- URL: https://letsship.ai/compare/devin-alternatives
- Author: Önder Ceylan
- Published: 2026-10-16
- Last reviewed: 2026-10-16

Devin alternatives with a cloud agent that opens a pull request include Codex cloud, GitHub Copilot cloud agent and Cursor cloud agents. Factory, Warp Factories, Tembo, OpenHands and SHIP are the others. This page compares where work starts, the models and coding agents, the checks on each change, and the price.

Devin is Cognition's autonomous AI software engineer. Each cloud session gets its own isolated machine. Work can start from the web app, a CLI, the API, Linear, Jira, Slack or Microsoft Teams. Each card below starts with the team that the alternative fits, from the alternative's own pages.

## Compare the eight alternatives on their own documentation

The table, the prices and the cards use only each product's own docs, pricing page or repository, and each card links its sources. Third-party lists for "devin alternatives" were read only to see which products appear for that search, and none is cited.

| Product                                            |  Linear |        Jira       |       Slack       |      Own model keys     |  Choice of agent  |    Self-hosted    |
| -------------------------------------------------- | :-----: | :---------------: | :---------------: | :---------------------: | :---------------: | :---------------: |
| [Devin](#devin)                                    | Yes |      Yes      |      Yes      |    Not documented    | Not documented | Not documented |
| [Codex cloud](#codex-cloud)                        | Yes | Not documented |      Yes      |    Not documented    | Not documented | Not documented |
| [Copilot cloud agent](#github-copilot-cloud-agent) | Yes |      Yes      |      Yes      |    Not documented    |    Pro+ and Max   | Not documented |
| [Cursor cloud agents](#cursor-cloud-agents)        | Yes | Not documented |      Yes      |    Not documented    | Not documented |      Yes      |
| [Factory](#factory)                                | Yes |      Yes      |      Yes      |   CLI and desktop app   | Not documented |    Airgap build   |
| [Warp Factories](#warp-factories)                  | Yes |      Yes      |      Yes      | Business and Enterprise |      Yes      |     Enterprise    |
| [Tembo](#tembo)                                    | Yes |      Yes      |      Yes      |         Yes         |      Yes      |      Yes      |
| [OpenHands](#openhands)                            | Planned |      Planned      |      Yes      |         Yes         |      Yes      |      Yes      |
| [SHIP](#ship)                                      | Yes |      Yes      | Not documented |         Yes         |      Yes      | Not documented |

A check means the product's own pages describe it. A dash means none of those pages states it, which is a statement about the pages, not about the product.

Each product is paid for in one of three ways. Prices are in US dollars a month, from each vendor's own pricing page, and they change often.

Pay a monthly plan

The plan covers the agent and its model use, up to the plan's limits.

**Devin:** $20 Pro, $200 Max, from $80 Teams.
The Free plan does not include the cloud agent. Past the plan's quota, extra usage bills at API prices.

**Codex cloud:** $20 ChatGPT Plus, from $100 ChatGPT Pro, $25 a user Business.
ChatGPT Free and Go do not include it, and an API key has no cloud features. Plus and Pro can buy more credits.

**Copilot cloud agent:** $10 Pro, $39 Pro+, $100 Max, $19 a seat Business, $39 a seat Enterprise.
Copilot Free does not include it. Runs draw GitHub AI Credits from the plan, and you can buy more.

**Factory:** $20 Pro, $100 Plus, $200 Max, $60 plus $40 a seat Teams.
No free plan. Sessions draw Factory credits for model use and Droid Computers.

Pay a plan, then pay for usage

Model use or machine time bills on top of the plan, or draws down its allowance.

**Cursor cloud agents:** from $30 Premium.
Runs bill at API prices for the model, under a spend limit that you set.

**Warp Factories:** $20 Build, $200 Max, $50 a user Business.
Build includes $20 of usage at API rates. Pay as you go bills 20% above API rates, and cloud runs also bill agent time.

**Tembo:** $60 Pro, $200 Max.
A free trial comes first. Model use and VM time draw from the plan's allowance, and VM time still bills when you bring your own key.

Bring your own model keys

Your model provider bills you for inference, and the plan pays for the platform.

**OpenHands:** $0 Cloud Individual.
Up to 10 conversations a day. The open-source version is free, and models run on your own key or the OpenHands provider at cost.

**SHIP:** $170 Starter, $480 Scale.
Free credits to start. Inference bills to your own model keys.

## Read each alternative on its own terms

### Devin

The agent that the other eight are compared with.

**Runs on:**
An isolated cloud machine for each session, or a local CLI

**Starts from:**
Web app, CLI, API, MCP, Linear, Jira, Slack, Teams, GitHub events, schedules, webhooks

**Models:**
Anthropic, OpenAI, Google and Cognition models. Pro, Max and Teams can link a ChatGPT plan.

**Agents:**
Devin

**Checks:**
It tests the app end to end and attaches a video of the screen. Devin Review reviews pull requests.

**Price:**
The cloud agent starts at Pro, $20 a month, and Max is $200. Teams starts at $80 a month. The Free plan does not include the cloud agent.

**Sources:**
* [Devin introduction](https://docs.devin.ai/get-started/devin-intro)
* [Devin pricing](https://devin.ai/pricing)
* [Self-serve plans](https://docs.devin.ai/admin/billing/self-serve)
* [Enterprise plans](https://docs.devin.ai/admin/billing/enterprise)
* [CLI models](https://docs.devin.ai/cli/models)
* [Automations](https://docs.devin.ai/product-guides/automations)
* [Testing and recordings](https://docs.devin.ai/work-with-devin/testing-and-recordings)
* [Devin Review](https://docs.devin.ai/work-with-devin/devin-review)
* [Enterprise deployment](https://docs.devin.ai/enterprise/deployment/overview)

### Codex cloud

Fits a team that uses ChatGPT plans and wants tasks to run in a cloud VM while laptops sleep.

**Runs on:**
A cloud VM for each task

**Starts from:**
ChatGPT on the web, desktop and mobile, the CLI, IDEs, `@codex` on GitHub, Linear, Slack

**Models:**
OpenAI models such as GPT-6.1 Sol, with a ChatGPT sign-in

**Agents:**
Codex

**Checks:**
The task shows the changes and test results. `@codex review` flags P0 and P1 issues.

**Price:**
It starts at ChatGPT Plus, $20 a month. Pro is $100, $200 or $500, and Business $25 a user. ChatGPT Free and Go do not include it.

OpenAI runs each Codex cloud task in a VM, and the task continues while your computer sleeps. You start it from ChatGPT, the CLI, an IDE, a `@codex` comment on GitHub, a Linear issue or Slack. A finished task shows its changes and test results, and you open a pull request when you are ready. Codex cloud needs a ChatGPT sign-in on Plus or above. Plus has a usage limit for each five-hour period, weekly limits may also apply, and Plus and Pro can buy more credits.

**Sources:**
* [Cloud](https://learn.chatgpt.com/docs/cloud)
* [Pricing](https://learn.chatgpt.com/docs/pricing)
* [Models](https://learn.chatgpt.com/docs/models)
* [GitHub](https://learn.chatgpt.com/docs/third-party/github)
* [Linear](https://learn.chatgpt.com/docs/third-party/linear)
* [Slack](https://learn.chatgpt.com/docs/third-party/slack)
* [Code review](https://learn.chatgpt.com/docs/code-review)

### GitHub Copilot cloud agent

Fits a team that plans in GitHub and wants the agent on GitHub's own pull requests.

**Runs on:**
A temporary cloud environment on GitHub

**Starts from:**
GitHub issues and pull requests, IDEs, the API, Jira, Slack, Teams, Azure Boards, Linear, schedules

**Models:**
Claude, Gemini, GPT and Grok models in a picker

**Agents:**
Copilot, with Claude and Codex agents on Pro+ and Max

**Checks:**
It runs tests and linters. Copilot code review comments on pull requests.

**Price:**
From Pro ($10). Pro+ $39, Max $100, Business $19 a seat, Enterprise $39 a seat. Copilot Free does not include it.

GitHub's cloud agent researches a repository, plans a change and implements it in a temporary cloud environment. You assign it an issue, or mention `@copilot` on any pull request to change that pull request. By default, GitHub Actions workflows wait for a person to approve them before they run on the agent's push. Pro+ and Max also list Claude and Codex as agents you can assign.

**Sources:**
* [About Copilot cloud agent](https://docs.github.com/en/copilot/concepts/agents/coding-agent/about-coding-agent)
* [Start Copilot sessions](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/cloud-agent/start-copilot-sessions)
* [Make changes to a pull request](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/cloud-agent/make-changes-to-an-existing-pr)
* [Change the AI model](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/cloud-agent/changing-the-ai-model)
* [About third-party agents](https://docs.github.com/en/copilot/concepts/agents/about-third-party-agents)
* [Copilot code review](https://docs.github.com/en/copilot/concepts/agents/code-review)
* [Copilot plans](https://github.com/features/copilot/plans)

### Cursor cloud agents

Fits a team that already works in Cursor and wants screenshots and videos of each change.

**Runs on:**
Cloud VMs, or your own machines with the self-hosted option

**Starts from:**
The Cursor app, web, mobile, the CLI, Slack, Linear, GitHub, the API, schedules, webhooks

**Models:**
A curated set of models

**Agents:**
Cursor's agent

**Checks:**
They build and test the change, with screenshots, videos and logs. Bugbot reviews pull requests.

**Price:**
From Premium ($30 a month). Cloud agents bill at API prices for the model.

Cursor runs cloud agents in isolated VMs with full development environments, or on your own machines. They build and test the change, and they record screenshots, videos and logs to demo it. You can take remote control of the agent's desktop while it works. Cloud agents come with the Premium plan and above, and they bill at API prices for the model.

**Sources:**
* [Cloud agents](https://cursor.com/docs/cloud-agent)
* [Automations](https://cursor.com/docs/cloud-agent/automations)
* [Bugbot](https://cursor.com/docs/bugbot)
* [Linear](https://cursor.com/docs/integrations/linear)
* [GitHub](https://cursor.com/docs/integrations/github)
* [Pricing](https://cursor.com/pricing)

### Factory

Fits a team that wants one agent, Droid, in a CLI, a desktop app, the web and Slack.

**Runs on:**
The CLI, the desktop app, or Droid Computers that Factory hosts

**Starts from:**
CLI, desktop, web, Slack, Linear, Jira, schedules, GitHub Actions

**Models:**
Native models, or your own keys in the CLI and desktop app

**Agents:**
Droid

**Checks:**
A GitHub Action posts inline review comments on pull requests.

**Price:**
Pro $20, Plus $100, Max $200 a month. Teams $60 plus $40 a seat. No free plan.

Factory's agent, Droid, works from the command line, a desktop app, the web, mobile and Slack. Linear, Jira and Slack delegations send work to Droid, which opens a pull request through the Factory GitHub App. Droid Computers are persistent machines that Factory hosts, and an airgap build exists for networks without internet. Your own model keys stay local in the CLI and the desktop app.

**Sources:**
* [Welcome to Factory](https://docs.factory.com/welcome)
* [Custom models (BYOK)](https://docs.factory.com/model-independence/byok)
* [Models](https://docs.factory.com/models)
* [Delegations](https://docs.factory.com/delegations)
* [Droid Computers](https://docs.factory.com/droid-computers/overview)
* [Code review in CI](https://docs.factory.com/software-factory/code-review-ci)
* [Airgapped deployment](https://docs.factory.com/enterprise/airgapped-deployment)
* [factory.com/pricing](https://factory.com/pricing)

### Warp Factories

Fits a team that wants its agent pipeline as code, with Claude Code or Codex for each agent.

**Runs on:**
Warp-hosted compute or your own infrastructure

**Starts from:**
Slack, Teams, GitHub, GitLab, Azure DevOps, Linear, Jira, webhooks, schedules

**Models:**
Warp's models, or team-managed inference on Business and Enterprise

**Agents:**
Warp Agent, Claude Code or Codex

**Checks:**
An implement agent adds tests and runs validation. A review agent checks that tests exist and pass.

**Price:**
Cloud runs start at Build, $20 a month with $20 of usage at API rates. Pay as you go bills 20% above API rates.

Warp Factories turns issues, tickets and Slack messages into reviewed pull requests. Each agent in a factory runs on the Warp Agent harness, Claude Code or Codex, and the factory never merges for you. Runs bill for inference, Warp-hosted compute and the platform. Enterprise can run the agents on your own infrastructure.

**Sources:**
* [Warp Factories](https://docs.warp.dev/factories/)
* [Platform](https://docs.warp.dev/platform/)
* [Platform FAQs](https://docs.warp.dev/platform/faqs/)
* [warp.dev/pricing](https://warp.dev/pricing)

### Tembo

Fits a team that starts work from many tools, Sentry included, and brings its own subscriptions.

**Runs on:**
A dedicated Linux VM for each session

**Starts from:**
Linear, Jira, GitHub, GitLab, Slack, Sentry events, schedules, webhooks, the API

**Models:**
Managed models, your own keys, Claude or ChatGPT subscriptions

**Agents:**
Claude Code, Codex, OpenCode, Pi, Cursor

**Checks:**
A review agent posts inline comments on every pull request.

**Price:**
A free trial, then Pro $60 and Max $200 a month. Each plan is a usage allowance that model use and VM time draw from.

Tembo runs any coding agent in a dedicated Linux VM for each session. Work starts from issues in Linear, Jira or GitHub, from Sentry errors, Slack, schedules or the API. You can connect your own keys, or a Claude or ChatGPT subscription. VM time still draws on the Tembo allowance when you bring your own key.

**Sources:**
* [Tembo docs](https://docs.tembo.io)
* [Models](https://docs.tembo.io/features/models)
* [Pull requests](https://docs.tembo.io/features/pull-requests)
* [Sandbox](https://docs.tembo.io/features/sandbox/overview)
* [Documentation index](https://docs.tembo.io/llms.txt), for the self-hosted pages
* [tembo.io/pricing](https://tembo.io/pricing)

### OpenHands

**License:** MIT

Fits a team that wants an MIT-licensed agent that it can run locally or host itself.

**Runs on:**
A local CLI, OpenHands Cloud, or your own VPC on Enterprise

**Starts from:**
GitHub, GitLab and Bitbucket issues, Slack, schedules, the API. Jira and Linear are listed as planned.

**Models:**
Any model LiteLLM supports, with your own key

**Agents:**
OpenHands, plus Claude Code, Codex and Gemini CLI

**Checks:**
A GitHub Actions workflow posts inline review comments.

**Price:**
Open source is free. Cloud Individual is free for up to 10 conversations a day.

OpenHands is MIT licensed and runs as a local CLI, in OpenHands Cloud, or in your own VPC on Enterprise. You start it with an `openhands` label or an `@openhands` mention on GitHub, GitLab, Bitbucket or Slack. Its Agent Canvas also runs Claude Code, Codex, Gemini CLI, Pi or OpenCode. Cloud Individual is free for up to 10 conversations a day.

**Sources:**
* [Introduction](https://docs.openhands.dev/overview/introduction)
* [OpenHands Cloud](https://docs.openhands.dev/openhands/usage/cloud/openhands-cloud)
* [GitHub installation](https://docs.openhands.dev/openhands/usage/cloud/github-installation)
* [Project management tools](https://docs.openhands.dev/openhands/usage/cloud/project-management/overview)
* [ACP agents](https://docs.openhands.dev/openhands/usage/agent-canvas/acp-agents)
* [Automated code review](https://docs.openhands.dev/openhands/usage/use-cases/code-review)
* [LLMs](https://docs.openhands.dev/openhands/usage/llms/llms)
* [openhands.dev/pricing](https://openhands.dev/pricing)

### SHIP

Fits a team that plans in Linear, Jira or GitHub Issues and wants each change through its own CI, a review and a test first.

**Runs on:**
A separate sandbox for each agent

**Starts from:**
Linear or Jira (assign the issue to SHIP), GitHub Issues (`@SHIP`), the `ship` CLI, MCP, the API

**Models:**
Your own Anthropic, OpenAI, OpenRouter or Z.ai keys

**Agents:**
`claude-code`, `codex`, `pi`, `kilo-code`, `open-code` per role

**Checks:**
Your CI, a Reviewer and a Tester against a preview. A failed gate sends the work back to the Builder.

**Price:**
Free credits to start. Starter $170 and Scale $480 a month. Inference bills to your own keys.

SHIP takes an issue through a Planner, a Builder, your own CI, a Reviewer, a preview deploy and a Tester. Any gate that fails sends the work back to the Builder with the feedback. Each role's harness and model is set in `ship.yml` ([schema](https://letsship.ai/docs/configuration/schema)), and inference bills to your own provider keys ([LLM credentials](https://letsship.ai/docs/getting-started/llm-credentials)). CI and preview deploys run in your own pipeline with your own credentials.

SHIP reports cost per mission and per stage, from list prices for the model that served each call. In SHIP's own [SWE-in-a-team study](https://letsship.ai/blog/swe-in-a-team), 13 builder configurations ran the same 20 tickets, one trial each, with API-equivalent cost. The claude-code builder on `claude-sonnet-5` resolved all 20 at $4.31 per resolved ticket.

**Sources:**
* [ship.yml schema](https://letsship.ai/docs/configuration/schema)
* [LLM credentials](https://letsship.ai/docs/getting-started/llm-credentials)
* [Artifacts](https://letsship.ai/docs/api/artifacts)
* [Pricing](https://letsship.ai/pricing)
* [SWE-in-a-team study](https://letsship.ai/blog/swe-in-a-team)

## Choose by how your team works

Requests start in Jira

* [Devin](#devin)
* [Copilot cloud agent](#github-copilot-cloud-agent)
* [Factory](#factory)
* [Warp Factories](#warp-factories)
* [Tembo](#tembo)
* [SHIP](#ship)

Requests start in Linear

* [Devin](#devin)
* [Codex](#codex-cloud)
* [Copilot cloud agent](#github-copilot-cloud-agent)
* [Cursor](#cursor-cloud-agents)
* [Factory](#factory)
* [Warp Factories](#warp-factories)
* [Tembo](#tembo)
* [SHIP](#ship)

Errors in Sentry should start work

* [Tembo](#tembo)

The agent must run on your own infrastructure

* [OpenHands](#openhands)
* [Cursor](#cursor-cloud-agents)
* [Warp Factories](#warp-factories)
* [Factory](#factory)
* [Tembo](#tembo)

Cursor and Tembo through a self-hosted option, Warp on Enterprise, and Factory through its airgap build.

You want an open-source agent

* [OpenHands](#openhands)

OpenHands is MIT licensed.

You want a video or screenshots of each change

* [Devin](#devin)
* [Cursor cloud agents](#cursor-cloud-agents)
* [SHIP](#ship)

SHIP's Tester attaches screenshots, videos or a trace of its test as proof.

Each change passes your CI, a review and a test before a person reviews it, with a harness per role

* [SHIP](#ship)

## Questions

### What are the best Devin alternatives?

Eight products document a cloud agent that takes a task and opens a pull request. They are Codex cloud, GitHub Copilot cloud agent, Cursor cloud agents, Factory, Warp Factories, Tembo, OpenHands and SHIP. Which one fits depends on where your work starts and what you want checked first. Each fact comes from the product's own pages.

### Is there an open-source alternative to Devin?

OpenHands is MIT licensed and runs locally, in OpenHands Cloud or in your own VPC on Enterprise. Its docs say it connects to any model LiteLLM supports, with your own key or its provider at cost.

### Which Devin alternative can run Claude Code or Codex?

Warp Factories, Tembo, OpenHands and SHIP each document runs of Claude Code and Codex. GitHub lists Claude and Codex agents on its Copilot Pro+ and Max plans. SHIP sets the harness per role in ship.yml. In SHIP, claude-code runs on your Claude subscription and codex on your ChatGPT subscription, or both run on API keys.

### Which Devin alternative starts from a Linear issue?

Devin, Codex, Copilot cloud agent, Cursor, Factory, Warp Factories, Tembo and SHIP each document a Linear trigger. With SHIP, you assign the issue to SHIP. OpenHands lists its Linear integration as planned.

### How much does Devin cost?

Devin's pricing page lists a Free plan, Pro at $20 a month and Max at $200 a month, and the cloud agent starts at Pro. Teams starts at $80 a month, and Enterprise is billed in Agent Compute Units at a contract rate.