// Side by side

How it compares

Four products put an AI agent to work in your repository. They differ on the things that decide whether one fits you: where it runs, who reviews the work, who merges it, and what you pay. Every cell below links to where it is stated. Where a vendor’s own pages do not say, the cell says “not stated” rather than guessing.

Checked 2026-09-15. These products change their plans, prices and model lists most months, and several of the features here are labelled preview or beta. The source links are the authority; this table is a snapshot of them.

The comparison

FULCRUMAXEDevinGitHub Copilot coding agentOpenAI CodexCursor Cloud Agents
How you give it workA GitHub Discussion in your repo. faqWeb app, Slack or Teams, Linear, Jira, API, CLI, or /devin on a PR. sourceAssign an issue, the agents panel, @copilot on a PR, Slack, Teams, Jira, Linear, VS Code. sourcechatgpt.com/codex, @codex on a PR, Slack, Linear, the CLI. sourceThe Cursor app, cursor.com/agents, Slack, @cursor on GitHub, Linear, API. source
Where it runsClaude Code sessions on your own machine. safetyPlanning and models in Cognition’s cloud; the dev environment in their cloud or a dedicated VPC. sourceGitHub Actions runners. sourceOpenAI-managed containers; the CLI runs on your machine. sourceCursor-managed virtual machines. source
Self-hosted?Yes — there is no hosted service. safetyPartly: Outposts run commands on your machines; inference and planning stay in Devin’s cloud. sourceSelf-hosted Actions runners are supported; the service is GitHub’s. sourceThe cloud agent, no. sourcePartly: your own workers run commands; Cursor runs the agent loop and the models. source
What it hands backPull requests, written in isolated worktrees. safetyPull requests. sourceCommits on a copilot/ branch and a draft pull request. sourceA diff; you choose to open a pull request. sourceA branch and a draft pull request. source
Who mergesIts own loop, and only once the gates the change needs are present. Keep branch protection on. safetyHuman engineers review and choose; Devin can merge where branch protection allows it. sourceA human: Copilot cannot approve or merge. sourceYou: “review before you merge”. sourceA human reviews before anything merges. source
Review built inSeparate code, security, acceptance and browser reviewer agents; each gate is a label. safetyDevin Review: a bug catcher and security scanning. sourceCodeQL, a dependency advisory check, secret scanning and Copilot code review, on by default. sourceCodex code review on pull requests, flagging high-priority issues. sourceBugbot, a separate product billed by usage. source
Cheapest plan with the agentFree software; you bring a Claude subscription or API key. costPro, $20 a month. sourceCopilot Pro, $10 a month. sourceChatGPT Plus, $20 a month. sourcePro, $20 a month. source
How usage is paid forBy your own Claude account. Our run measured a median of $29 per merged pull request. howA quota, then prepaid credits. sourceActions minutes plus AI credits, usage-based since June 2026. sourceLimits per five-hour window and per week, then credits. sourceAPI pricing for the chosen model, with a spend limit set first. source
ModelsClaude, through Claude Code, on your subscription or API key. startNot stated for the cloud agent.A choice including Claude, GPT and Gemini models. sourceGPT-5.6 Sol in the cloud, which needs a ChatGPT sign-in. sourceA curated selection, including Cursor’s own. source
Open sourceYes, AGPL-3.0. licenceNot stated.Not stated.The CLI is Apache-2.0; the cloud agent is not open source. sourceNot stated.
// Fair is fair

Where the others are stronger

They are hosted: nothing to keep running on a machine of your own, and work continues when your laptop is shut. They take work from where teams already talk — Slack, Jira, Linear, the editor — rather than from GitHub Discussions alone. They are products with support behind them, where FULCRUMAXE is an experimental open-source project built for one developer. And they choose from several model vendors, where FULCRUMAXE runs on Claude.

// The difference

Where FULCRUMAXE is different

Review is the core of it rather than an add-on. A change is written by one agent and has to pass separate code, security, acceptance and browser reviewers, recorded as labels the merge step reads. Because of that, its own loop merges the work once the gates are present — a deliberate trade-off the others make the other way, by leaving the merge to a person. How the gates work, and where they fail.

It runs on your hardware and your own Claude credential, the source is AGPL-3.0, and the team’s own work is public: every pull request it merged is on how the work ships, and what it cost is measured rather than quoted on the cost page.

It is the wrong choice if you want a hosted service, work from an editor or a chat tool, need vendor support, or cannot keep a Linux machine running the loop.