A project that is not code
It holds plans, tasks, notes, decisions and documents. With no folder there is nothing to scan: the app skips it without an error.
For marketing, HR, finance and creative work
Give your AI assistant a project with no code: the plan, the deliverables, the decisions and the brief stay in one place. It starts from them, not from zero.
In the product todayPartly covered
Proofs last checked on 7 Oct 2026
“Every AI tool talks about files and branches. My work is a launch date and a budget.”
The menus, the examples and the install guides are written for developers, so you start by translating them into your own work.
“I paste the brand rules and the brief again in every new chat.”
The assistant forgets between conversations, so the tone of voice, the audience and the budget cap are retyped each time.
“We changed the plan in March. Nobody wrote down why.”
A decision lives in a chat that scrolled away. Weeks later two people remember two versions.
“The plan is in a spreadsheet, the talk in three chats, and the date in my head.”
You are the only link between the deliverables, so you are the one who notices that the invitations were waiting for a date.
“Is the figure the assistant just quoted still true?”
Last quarter’s budget cap, a salary band that moved: the assistant repeats it with the same confidence. Nothing tells you it is old.
It holds plans, tasks, notes, decisions and documents. With no folder there is nothing to scan: the app skips it without an error.
An Objective carries the date and shows when it is overdue. The Plan under it lists the deliverables as Tasks, and a task can wait for another one.
Write the tone of voice or the budget cap as a Guideline note marked high or critical. The assistant gets it at the start of every conversation in that project.
A Decision keeps the choice, the reason and the options you turned down. The assistant can search them before it proposes something you already ruled out.
Today lists what waits for your answer, what stopped and can be resumed, and what moves on its own. It also holds your own tasks and your day.
Attach a brief, a call transcript or a CSV export of your budget to a message: the assistant reads the text. Word and PDF files are refused and Excel and PowerPoint files are kept unread in the published app.
A skincare brand launches a new range on 12 November: ten deliverables, two freelancers and one budget.
YouThe plan lives in a spreadsheet. The talk with the assistant lives in four chats.
YouEach new chat starts blank: you paste the tone of voice and the audience again.
YouOn Thursday you decide there is no price in the press kit. On Monday the assistant writes the price in the draft.
YouOnly you know that the newsletter waits for the press kit, so you check it by hand.
YouYou ask the assistant to create a project with no code called “Autumn launch”, then add an Objective dated 12 November.
AssistantIt writes a Plan with the ten deliverables as Tasks: landing page, newsletter, press kit, social posts. The newsletter waits for the press kit.
YouYou write the tone of voice as a Guideline note, and attach the brief and the budget exported as a CSV.
Project OrchestratorThe Decision “no price in the press kit” is kept with its reason. The next conversation can find it.
AssistantIt stops to ask which budget to use for paid ads. The question appears in Today, and you answer it there.
Monday starts from one screen: what waits for you, what is late, and the choices already made. Sending and publishing still happen in your own tools.
You say “campaign” and “deliverable”. Project Orchestrator says Project and Task: same things, shorter names.
“a campaign, a recruiting round, a budget”
Project
A body of work with its own plans, notes and decisions.
“a project without code, a campaign file”
work
The kind of project with no code folder. You do not need to name it: leave the Folder field empty.
“the launch, the target”
Objective
What the work is heading toward.
“the editorial calendar, the budget steps”
Plan
How an objective gets done: ordered tasks and steps.
“a deliverable”
Task
A unit of work inside a plan.
“our brand rules, our templates”
Note
A Guideline note is a rule the assistant follows; a Gotcha note is a trap to avoid.
“the approved direction”
Decision
A choice that was made, with its rationale and alternatives.
“the budget sheet, the deck, the brief”
Document
Spreadsheets, decks and files attached to your work.
“my AI helper”
Assistants
A conversation with an AI that works on your project; Today shows which ones are running.
Words this page leaves out : repository, MCP, wave, knowledge graph, API
A project is either software or work. Work is defined as plans, tasks, notes and attachments with no source tree, and it can be created without a folder.
Asked to create a project, the assistant passes its kind to the server. A test creates a project named Hiring of kind work.
The opening context of a project conversation lists its active plans, its active Guideline notes of high or critical importance, its active Gotcha notes and its Objectives with their dates.
The list of notes shows “stale” with a percentage once a note has not been confirmed for long enough. The Confirm button on the note says it still holds.
Text, Markdown and CSV are always read. PDF, Word, Excel and PowerPoint reading sits behind build options that are off by default, and the desktop release is built without them: a PDF or a .docx is refused, an Excel or PowerPoint file is stored and not read.
At most 60,000 bytes of a document’s text go into one message. The rest is cut, and the assistant is told it was cut.
The side menu is built from one list without looking at the kind of project, so Code, Architecture and Deployments stay visible on a project with no code.
Nothing here is hidden: these are the things you might assume and that are not true yet.
The side menu is the same for every project. Code, Architecture and Deployments stay visible on a project with no code: ignore them.
The project form cannot choose the kind “work”. Leave Folder empty and nothing is scanned; to store the kind itself, ask the assistant.
The list of projects shows an amber “Never synced” on a project with no folder. Nothing is wrong: there is just nothing to sync.
PDF and Word files are refused, and Excel and PowerPoint files are stored without being read. Export to CSV or paste the text.
The Today screen is in French in the product. Most other pages are in English, and only the side menu is translated.
The chat welcome offers code actions (Impact analysis, Code search, Architecture) next to Next task, Plan something and Roadmap. Only the last three fit your work.
Launching a whole plan from Today is built around code projects: it uses git branches and build checks. It has not been tried on a plan with no code, so work through the tasks in the conversation.
There is no ready-made campaign, hiring or budget template: you or the assistant write the plan.
A shared space with roles and rights, such as a hiring file seen by two people and not a third, is planned and not available.
Download it for your system, then follow the setup screens. It asks for Docker Desktop and a chat engine, and shows each step as it goes.
DownloadIn Projects, press New project, give it a name and leave the Folder field empty. Or ask the assistant for “a project with no code, kind work”.
Add an Objective with its date. Then tell the assistant what the deliverables are and ask for a Plan, with the order they depend on.
Add a Guideline note of high importance for the tone of voice or the budget cap. Attach the brief as text, Markdown or a CSV export.
Answer what waits for you, resume what stopped, and write each choice as a Decision. See a worked example of a plan with no code.
Use casesNot to use it. The install needs no terminal: you add Docker Desktop and a chat engine, Claude Code by default, then the app shows each step. The assistant has its own cost with its provider.
Not in the published app today. Text, Markdown and CSV are read. Export the sheet as CSV, or paste the text of the document into the conversation.
Notes and decisions are stored in a database on your computer, and the original files on its disk. What you write or attach in the chat is sent to the service that runs the assistant, under its terms. Project Orchestrator makes no compliance claim, so check your own rules before putting personal data in.
Not as a shared space with roles. Roles and rights are planned, not available, and sharing between two installations is still in progress. Today one installation is one person’s workspace.
No. Project Orchestrator keeps the plan, the notes and the thread. Sending and publishing happen in your own tools, or in a tool you connect to the assistant.
The setup offers Claude Code first. Other providers can be added in Settings, but they have not been tried here against real services, so treat them as in progress.
The app is free and open source (MIT). The assistant you connect to it has its own cost.
Download
One-click install
There is no Project Orchestrator account to create.
Free · MIT license · Bring your own AISee what it costs
Version 0.0.19 · 13 Nov 2026
The app installs on a computer. Pick the one you use.
Prefer a terminal?
Homebrew · Mac and Linux. Installs orchestrator, orch and mcp_server.
brew install this-rs/tap/project-orchestratorDocker Desktop
Runs the database and the search engine the app relies on. The app starts them for you. Get Docker Desktop
Claude Code
The default engine for chat. The AI itself is not included: with Claude Code, you use your own Claude account, and the app can install it for you. Other engines (Codex, an OpenAI-compatible model, an ACP agent) are available from Settings — newer, in alpha. Get Claude Code
At first launch
A setup wizard in four short parts checks Docker, installs Claude Code if it is missing and downloads the search model.
Runs the two services that hold the project memory (Neo4j and Meilisearch).
Open the downloaded .dmg, drag Docker into Applications, then open Docker once and wait for the whale icon to stop moving.
Or in a terminal
brew install --cask dockerCheck that it works
Each line should print a version number. If you see « command not found », open a new terminal window and try again.
docker --versiondocker compose versionDocker must be running (open it once) before you start Project Orchestrator. Installation page of the publisher
The assistant Project Orchestrator works with. It uses your own Claude account.
Paste the command in a terminal. It installs everything it needs and asks for your password only if required.
Command
curl -fsSL https://claude.ai/install.sh | bashCheck that it works
Each line should print a version number. If you see « command not found », open a new terminal window and try again.
claude --versionRun claude once to sign in. Installation page of the publisher
Free · MIT license · Bring your own AI See what it costs
Try it: start a task in any window
Download
Pick the file for your system above. There is no account to create.
Open
Open the file. A setup wizard checks Docker, installs Claude Code if it is missing and downloads the search model.
Connect your AI
Chat runs on Claude Code by default; other engines are available from Settings (alpha). If it asks you to sign in, type this once in a terminal.
claudemacOS, Apple Silicon
The app for Macs with an M1 chip or later.
Project.Orchestrator_0.0.19_aarch64.dmg · 87.1 MB
macOS, Intel
The app for Macs with an Intel chip.
Project.Orchestrator_0.0.19_x64.dmg · 89.8 MB
macOS, Intel (macOS 10.15 to 13.3)
For Intel Macs on macOS 10.15 to 13.3. Without local embeddings: use an HTTP provider such as Ollama.
Project.Orchestrator_0.0.19_x64-legacy.dmg · 47.7 MB
Linux, AppImage
One file that runs on most Linux distributions (x86_64).
Project.Orchestrator_0.0.19_amd64.AppImage · 163 MB
Debian and Ubuntu, x86_64
Package to install with dpkg or apt.
Project.Orchestrator_0.0.19_amd64.deb · 98.1 MB
Debian and Ubuntu, arm64
Package to install with dpkg or apt, for ARM64 machines.
Project.Orchestrator_0.0.19_arm64.deb · 94.4 MB
Fedora and RHEL, x86_64
Package to install with dnf or rpm.
project-orchestrator-0.0.19-1.x86_64.rpm · 61.5 MB
Fedora and RHEL, arm64
Package to install with dnf or rpm, for ARM64 machines.
project-orchestrator-0.0.19-1.aarch64.rpm · 56.7 MB
Homebrew
Mac and Linux. Installs orchestrator, orch and mcp_server.
brew install this-rs/tap/project-orchestratorInstall script
Mac and Linux. Latest release into ~/.local/bin. Add --no-frontend for the light variant.
curl -fsSL https://raw.githubusercontent.com/this-rs/project-orchestrator/main/install.sh | shPowerShell
Windows. Installs into %LOCALAPPDATA%\orchestrator\bin.
irm https://raw.githubusercontent.com/this-rs/project-orchestrator/main/install.ps1 | iexDocker
Image for amd64 and arm64, with the web interface.
docker pull ghcr.io/this-rs/project-orchestrator:latest# API only, no dashboard: a version tag with the -api suffix# docker pull ghcr.io/this-rs/project-orchestrator:0.0.19-apiorchestrator, orch and mcp_server, with the web interface included. Lighter versions without it are on the release page.
macOS, Apple Silicon
Programs without the app window: orchestrator, orch, mcp_server
orchestrator-full-0.0.19-macos-arm64.tar.gz · 81.9 MB
macOS, Intel
Programs without the app window: orchestrator, orch, mcp_server
orchestrator-full-0.0.19-macos-x86_64.tar.gz · 82.8 MB
Linux, x86_64
Programs without the app window: orchestrator, orch, mcp_server
orchestrator-full-0.0.19-linux-x86_64.tar.gz · 91.1 MB
Linux, arm64
Programs without the app window: orchestrator, orch, mcp_server
orchestrator-full-0.0.19-linux-arm64.tar.gz · 85.6 MB
Windows, x86_64
Programs without the app window: orchestrator.exe, orch.exe, mcp_server.exe
orchestrator-full-0.0.19-windows-x86_64.zip · 92.8 MB
The desktop app starts Neo4j and Meilisearch in Docker for you. With the command line, one compose command does it: follow the quickstart.
More for developersWhat you should see. A list of checks. On the very first launch the Docker lines say “Setup pending”.
What to do. Wait for the setup to open: the start screen only checks what is installed.
What you should see. A green line says “Docker Desktop is running” under two cards, “Docker (recommended)” selected.
What to do. Keep “Docker (recommended)”. The app looks for Docker Desktop. When it says “Docker Desktop is running”, press Next. If it says Docker is missing or not running, use the button next to the message, then wait: the app checks again by itself. The services use the local ports 7474, 7687, 7700 and 4222, and the app itself uses 6600.
What you should see. Three choices (No authentication, Password, OIDC / OAuth), the first one selected.
What to do. On a computer only you use, keep “No authentication” and press Next. On a shared or public network, choose “Password” and set an email and a password: without sign-in, the app’s server accepts connections from your whole network.
What you should see. Claude Code CLI shows a green check once installed (until then: “Claude Code CLI is required” and an install button), and the search model is marked ready.
What to do. If “Claude Code CLI is required” is shown, press “Install Claude Code CLI”. Then let the app download the search model when it offers to; the size is shown on screen. Next unlocks when both are ready. If you have not signed in to Claude yet, see “If it does not work” below.
What you should see. A green “Configuration saved!” message and a “Restart Application” button.
What to do. Press “Generate Config & Save”. When “Configuration saved!” appears, press “Restart Application”. A switch on this screen controls whether the app checks for updates at start-up.
What you should see. A checklist (Docker Desktop, Neo4j, Meilisearch, NATS, Backend server) turning green one line at a time.
What to do. On this second start the app downloads the three images it runs on, then starts them. Later starts reuse the images and are quicker. When every line is green, the main window opens. If a line says “Taking longer than expected”, wait. If a “Continue anyway” button appears, see “If it does not work”.
macOS 11 or later on Apple Silicon (M1 and later). On Intel: macOS 13.4 or later, or macOS 10.15 to 13.3 with the older-macOS file, which has no local embeddings.
Download Docker Desktop from Docker’s page, open the file, drag Docker to Applications, then open it and wait until it says it is running.
Get Docker DesktopDocker Desktop is open and reports that it is running. It is Docker’s own screen, so it is not reproduced here.
Open the .dmg, drag Project Orchestrator to Applications, then open it from there. If macOS says it cannot check the app, we could not verify how the build is signed: allow it in System Settings, Privacy & Security, with “Open Anyway”.
The three problems you are most likely to meet, with what the app shows.
What you see. The app says “Docker Desktop is not running” or “Docker Desktop is required”.
What to do.
What you see. Neo4j or Meilisearch stays “Unhealthy”, or the app says it failed to start services. The services need the local ports 7474, 7687, 7700 and 4222.
What to do.
Only if you are comfortable with a terminal, this shows which program uses the port:
lsof -i :7687What you see. The setup says “Claude Code CLI is required”, or the chat says it has no Claude login.
What to do.
Type this and press Enter:
claudeWindows, 64-bit.
Download Docker Desktop from Docker’s page, run the installer, then start Docker Desktop from the Start menu and wait until it says it is running.
Get Docker DesktopDocker Desktop is open and reports that it is running. It is Docker’s own screen, so it is not reproduced here.
Run the installer and follow the wizard, then start Project Orchestrator from the Start menu. Windows may show “Windows protected your PC” because no signing certificate is set in the build configuration: choose “More info”, then “Run anyway” if you trust the download.
The three problems you are most likely to meet, with what the app shows.
What you see. The app says “Docker Desktop is not running” or “Docker Desktop is required”.
What to do.
What you see. Neo4j or Meilisearch stays “Unhealthy”, or the app says it failed to start services. The services need the local ports 7474, 7687, 7700 and 4222.
What to do.
Only if you are comfortable with a terminal, this shows which program uses the port:
netstat -ano | findstr :7687What you see. The setup says “Claude Code CLI is required”, or the chat says it has no Claude login.
What to do.
Type this and press Enter:
claudeAppImage for Intel/AMD; .deb and .rpm packages for Intel/AMD and ARM64.
Follow Docker’s page for your distribution, then start Docker and wait until it says it is running. The app also recognises Docker installed without the Desktop application.
Get Docker DesktopDocker is running. It is Docker’s own screen, so it is not reproduced here.
For the AppImage: in your file manager, open the file’s properties and allow it to run as a program, then double-click it. For a .deb or .rpm: open it with your software installer, then start Project Orchestrator from your applications menu.
The three problems you are most likely to meet, with what the app shows.
What you see. The app says “Docker Desktop is not running” or “Docker Desktop is required”.
What to do.
What you see. Neo4j or Meilisearch stays “Unhealthy”, or the app says it failed to start services. The services need the local ports 7474, 7687, 7700 and 4222.
What to do.
Only if you are comfortable with a terminal, this shows which program uses the port:
lsof -i :7687What you see. The setup says “Claude Code CLI is required”, or the chat says it has no Claude login.
What to do.
Type this and press Enter:
claude