Field bulletin · Install Potluck
Install on one machine. Or all of them.
Potluck is a desktop app that runs open models on hardware you own. Chat with them, give your coding agents a persistent memory over MCP, and join your machines into one private network with the WireGuard mesh built into the app. Choose local inference or route a request to your own paired machines. Trusted-circle inference and the open contributor pool are still in development.
Published versions: Apple Silicon Mac and Linux 0.1.6; Windows 0.1.5. Intel Mac downloads are paused.
Before you start
| Item | Requirement |
|---|---|
| Mac | macOS 13+, Apple Silicon. Intel downloads are paused while we repair and validate the native build. Signed and notarized, so it opens normally, no right-click needed. |
| Windows | Windows 10+. The installer is unsigned, so SmartScreen warns once (More info, then Run anyway). We publish a SHA-256 for every build so you can verify it yourself. |
| Linux | A .deb for Debian, Ubuntu, and Pop!_OS, plus a portable .AppImage for other distributions. 64-bit x86 (amd64). |
| Cross-machine | The WireGuard mesh is included, and machines pair inside the app. Enabling it may request administrator permission for a background service and network adapter. No separate VPN account is needed. |
| Disk | Models are the bulk of it: a few GB for a starter model, more if you pick larger ones. The app shows the download size before it fetches anything, and every download is SHA-256 verified. |
| Access | Open. Free to download, free to run locally. No account needed for local inference. Pairing and account services may need connectivity or sign-in. |
Install
One installer per platform. The app carries everything it needs: the inference engine, the memory store, the MCP server, and the mesh. There is no step two where you install something else.
macOS
- Download the Apple Silicon (arm64) DMG for M1 and newer. Intel downloads are temporarily paused.
- Double-click the DMG, drag the app to Applications, then eject.
- Open it from Applications. The build is notarized, so it opens normally with no right-click. First launch unpacks the bundled engine (~10-20 seconds).
Windows
- Download the installer .exe.
- On the SmartScreen warning, click "More info" then "Run anyway." Windows builds are unsigned; the same binaries run on our own machines, and you can match the published SHA-256 before you run it.
- After install, Potluck appears in the Start menu.
Linux
- On Debian, Ubuntu, or Pop!_OS, download the .deb and install it with
sudo apt install ./potluck-ai-desktop_0.1.6_amd64.deb, then open Potluck from the app menu. - On other distributions, download the .AppImage, make it executable with
chmod +x, and run it directly. - Turning on the mesh installs a small background service. It asks for your password once through the system polkit prompt, no terminal required.
First run
The app walks you through setup in four short steps. No account is required for local use. Model downloads and optional network or account features need a connection.
- Hardware check. The app reads your RAM and GPU and tells you what it can run well on this machine.
- Pick a starter model. It downloads with a visible size and progress, hash-verified before it loads.
- Pair your other machines (optional). Machines on the same network find each other; a short pairing code confirms it is really yours.
- Readiness check. Real probes, not a green dot: can this machine actually run inference, is a VPN fighting the mesh, is the mesh port reachable.
Bring your coding agents
A compatible MCP client, such as Codex, Cursor, Zed, Cline, Continue, or Claude Code, can use Potluck as its persistent memory: project facts, decisions, and multi-session tasks that survive across sessions. Access from another machine requires optional peer memory sharing.
You do not hand-write the config. Open Settings, then Connect tools, pick your agent, and the app generates the exact MCP entry pointing at its bundled server. Paste it where your agent expects MCP servers and restart the agent. It will see memory_search, memory_save, task_create, and the rest of the Potluck tools.
The fastest proof it works: ask the agent to remember something, then find it in Potluck's memory browser. The agent activity view shows connected MCP sessions with tool-call metadata; it does not expose external agents' raw prompt payloads.
Your machines, one network
Pairing happens inside the app. Machines on the same network discover each other; you confirm with a short pairing code. Under the hood this builds a private WireGuard mesh between machines you own, with no third-party VPN account and no config to edit.
For another machine to answer, it must be reachable, have the requested model loaded, and have serving enabled. Choose My Machines in chat to use eligible paired computers. Keep local mode selected to run inference on this computer. Trusted-circle inference and the open pool are not ready in this release.
Memory works across the mesh too, if you opt in per machine: your agent on the laptop can search memories saved on the desktop. Peers only ever reach the narrow peer endpoints; your full memory store, tasks, conversations, and settings stay loopback-only. Peer reads are read-only; writes stay local.
Honest limits
- Windows installers are unsigned. The Mac build is notarized, so Gatekeeper opens it normally. Windows stays unsigned, so SmartScreen warns once; we publish a SHA-256 for every build so you can verify integrity without a signature.
- Trusted-circle inference and the open pool are in development. Use local inference or My Machines in the current release. The wider contributor network is not ready for dependable public use, and the contribution toggle does not launch an open-pool contributor in this build.
- Peer memory sharing is per-machine, all or nothing. When you opt a machine in, paired peers can search that whole store. Per-project sharing flags are on the roadmap.
- Mesh membership is the trust boundary. Any machine paired into your mesh can call the peer endpoints you opted into. A signed-nonce peer credential replacing reachability-as-trust is planned hardening.
Where to go next
- /how-it-works · the routing scopes, the mesh, and what a contributor can and cannot see.
- /benchmarks · measured numbers across memory retrieval, inference, and cross-machine latency on Mac/Linux/Windows.
- /manifesto · why Potluck is built as a member-operated network and a founder-led company.
- /roadmap · what is shipped, in flight, designed, and to be decided.
Questions, or want to shape it?
Join the Discord