A shared place for a project’s brief, documents, files and tasks. Each person on the team opens it in the app or from their own AI (Claude, Claude Code, Codex, or ChatGPT on its Business, Enterprise and Edu plans), and whatever their AI changes is saved to the project under their name. Every past version is kept, and every project is also a git repository you can clone.

A shared Claude or ChatGPT project gives everyone on it the same files and instructions to start a chat from, inside that one AI. In Claude each person’s chats stay their own unless they share one; in ChatGPT members can see each other’s chats, and ChatGPT can draw on them. Either way, what a chat produces reaches the project’s files only when someone saves or uploads it, and a teammate who works in another AI can’t open the project from there (how sharing works in Claude and in ChatGPT). In Alcoven your AI edits the project’s documents and tasks directly, the change is saved under your name, and teammates see it from Claude, ChatGPT, Codex or the app. Anyone you invite by email can join, whichever AI they use, and clients read free.

An Alcoven project is a git repository: Claude Code and Codex clone it and push to it. It is also open to the people on the team who never use git. They open it in Claude or ChatGPT, or in the app, where Word files, PDFs and spreadsheets open in a preview and tasks sit beside the documents. Clients join free as readers. Your code can stay on GitHub: link a repository and it shows up as a folder in the project, and changes to it go back to GitHub as pull requests.

Free covers one project and up to five people writing to it, with no card. Solo is $8 a month, or $80 a year, for one person writing on any number of projects. Team is $12 per person writing a month, billed yearly, or $15 per person writing, billed monthly. Prices are in US dollars. See pricing.

You pay for each person who can write to a project. Readers, clients and agents join free, on any plan.

The agent in the app is part of every plan’s price, so its included use costs nothing extra. Free includes $1 of agent use a month for the team, Solo includes $3 a month, and Team includes $3 a month per person writing, shared by the team. When the included use runs out, the agent pauses until next month, unless the team adds more in advance ($10 of agent use for $11, before tax). The agent spends only what the plan includes and what the team has paid for, so nothing is billed afterwards. Working from your own AI costs nothing extra either, because we run no model for it: over git or MCP, from Claude, Claude Code, Codex, or ChatGPT on its Business, Enterprise and Edu plans.

The agent in the app pauses until next month, unless the team adds more. Any team, Free included, can add $10, $20 or $50 of agent use in advance: $10 of agent use costs $11, plus any tax for your country, and what the team adds carries over from month to month for 12 months. On Solo and Team, the team can also have it added automatically, up to a monthly limit it sets. Nothing is billed afterwards. Working from your own AI never counts, because we run no model for it.

Yes. Clone the project with git and work on it from Claude Code, Codex or any coding agent, then push. Or add Alcoven to an AI app that speaks MCP, such as Claude, or ChatGPT on its Business, Enterprise and Edu plans, and sign in once to reach every project you’re on (how to set it up in Claude or ChatGPT). What your AI changes comes back under your name, and it costs nothing extra on any plan.

Yes. Bring the project’s numbers in from a CSV file in the project, a Google Sheet, Google Analytics, a linked GitHub repository, or numbers your product sends, and keep the ones that matter on the project’s home. Add Alcoven to your AI, or ask the agent in the app, and it reads them with the project’s documents and tasks, so it answers from the plan, the work and the numbers together, and says where each number came from. How widgets work.

Yes. The project’s home gives each person one next step with its reason, and shows everyone who writes what the plan still lacks. Write the plan’s phases and this week’s focus in a short file, and Alcoven reads the tasks and numbers against it. Ask your AI what to do, and Alcoven gives it the same step. The focus guide has every line.

Add the product and growth skills from the skills page to your project. The agent in the app follows them, and each person’s AI is given them when it opens the project. Ask something broad, like how to make more money, and it first asks a few plain questions: whether customers stay and pay, how new ones find you, then price and cost.

Each person opens the project from the AI they already use, or in the app, and everyone works from the same files. If you move from ChatGPT to Claude, the project stays as it is: open it from Claude instead.

Keep the project in Alcoven, and each person opens it from their own AI or in the Alcoven app. Claude adds Alcoven as a custom connector on every plan. ChatGPT on the web adds it on Business, Enterprise and Edu. On Pro it can add Alcoven but only read the project. On Free, Go and Plus it can’t add it, so those people use Claude’s free plan or the app. Claude Code and Codex clone the project with git. What either AI changes is saved to the same documents under that person’s name, and the other half sees it the next time their AI opens the project (how to set it up in each AI, plan by plan).

Yes. A skill is a document in the project, in the open Agent Skills format: a name, when to use it, and the steps. The agent in the app follows it, and each person’s AI is given it when it opens the project, in Claude, Claude Code, Codex, or ChatGPT on its Business, Enterprise and Edu plans. Claude’s Team and Enterprise plans share skills too, inside one Claude organisation; a skill in an Alcoven project goes with the project, to everyone on it, clients and freelancers included. Skills you can add, free, at alcoven.co/skills.

Correct the passage in the project’s document, in the app or by asking your own AI. The correction is saved under your name, and the next AI that reads the document, your teammate’s included, reads the corrected version. If you’d rather your teammate make the change, or you can only read the project, leave a note on the passage that asks them. It waits on their home in Alcoven until someone closes it. When they open the project from their AI, it gets the note; in a git clone, the note is a file in the notes folder.

If the document is in an Alcoven project you’re on, open it and choose Why this? on a passage. It shows who wrote that passage, with which AI and when. If the request was recorded with the change, it also shows what they asked and what their AI read for it. Alcoven started recording requests on 15 October 2026; a change pushed with git carries one only when its commit message says what was asked. Everyone on the project can open Why this?, readers included. A copy sent as a file or pasted into a message carries none of this.

It holds what a project knows: the brief, the documents, the tasks and every change, with who made it. Tasks are open or done, and there are no boards to groom.

The people and agents you add, each allowed to read, write or manage. Other projects stay out. Nothing is public.

We don’t train models. The agent in the app runs on Amazon Bedrock, and AWS says that neither AWS nor the model providers use what goes into or comes out of Bedrock to train any model (Amazon Bedrock FAQs). When you work from your own AI, that tool’s own terms apply.

Clone the project with git, on any plan: every document, task and past version comes with it. Cancel any time. Your projects stay readable, and you can still clone them. You can ask for a refund within 14 days of a payment.

Yes. One project is free, and Solo covers any number of projects for one person writing. When you add a person later, they start with everything you let them see.

Deep Node Studios Yazılım ve Teknoloji Limited Şirketi, in Kadıköy, İstanbul. Paddle handles payments as our merchant of record. Write to us at info@alcoven.co.