A model-agnostic agent loop
Plan, pick one tool, observe, repeat. Talks to Ollama, llama.cpp, LM Studio, vLLM, or any OpenAI-compatible /v1/chat/completions endpoint on localhost or your LAN. Swap the weights without rewriting the product.
computer.vodka is an ai agent harness. It is the control loop around the model you already run. Each turn is the same: plan, pick one tool, read the result, then stop or ask before a step that is hard to undo. Tools, memory, and approvals stay in one folder on your disk. The install is free. Hosted extras are optional and metered.
Public beta opens Q4 2027, after private-trial bugs are actually fixed. Thanks for waiting.
A harness is the runtime around a model: planner, tool runner, workspace root, session log, and a permission gate. You talk here. It proposes a plan, calls one tool, reads the output, and waits if the next step would delete, overwrite, install, or send. Quality follows the weights you point it at. This page is a preview of that chat shell. The real loop starts after you install.
Tap an app to see how a connector would show up in the loop. Off means that tool is never offered to the model. Live OAuth ships with the trial.
Leave it blank for now if you only want the local chat. The first message in any text thread is password-checked, so a random number cannot act for you.
Local files stay inside one folder. Memory is markdown in that folder. This preview cannot see your disk.
These are the connectors the harness can switch on inside the chat. Hover or tap the row to pause it. Live OAuth ships with the trial. Hosted extras keep them alive when the laptop is closed.
Most products hide the model and ship your files to a GPU farm. A harness does the opposite. It is a small process on your machine: a planner, a strict tool schema, markdown memory, and a gate in front of writes. You attach Llama, Qwen, Mistral, Gemma, or an OpenAI-compatible server on localhost or your LAN. Swap the weights and the product does not change. Free local quality is exactly as good as those weights. The subscription only covers work a closed laptop cannot do alone, like always-on text and multi-device sync.
Plan, pick one tool, observe, repeat. Talks to Ollama, llama.cpp, LM Studio, vLLM, or any OpenAI-compatible /v1/chat/completions endpoint on localhost or your LAN. Swap the weights without rewriting the product.
Every path is resolved against one workspace folder. Memory is markdown you can open. The installed harness does not phone home with prompts or file contents.
Rolling summaries, a small tool schema, and interruptible streams so a long session still fits on Apple Silicon or a strong CPU.
Deletes, overwrites, installs, and outbound sends wait for a yes. You see the plan and the diff before anything hits disk.
read, write, search, shell, fetch, diff, plus connectors you toggle in the chat. Enough to finish work. Not a kitchen sink.
Mail, calendar, docs, chat, and the rest sit behind the Apps toggle. Off means the tool is never offered to the model.
Give it the number you want watched. SMS and WhatsApp then drop a task into the same loop. The first message in a thread is password-checked so a random sender cannot act for you.
The loop on your disk is free and follows your model. Cloud fallback, multi-device sync, always-on text, and scheduled jobs are usage-billed.
No account to babysit for the local path. You go from a trial request to a working loop in one folder. After that, every turn is plan, one tool call, observe, then continue or stop. Quality is the model you attach. Hosted extras stay optional.
Open the interface below and tell the agent you want in, or just type your email. It collects what it needs and sends the request for you.
macOS, Linux, or Windows. Point it at Ollama, llama.cpp, LM Studio, or any OpenAI-compatible endpoint. After setup the local loop does not need an account.
Point it at a folder, say what you want in plain language, and let the loop plan. Approve writes, deletes, and installs. Read the transcript after.
The site is a preview. The installed product is one process: planner, tool runner, memory on disk, policy gate. That is the whole idea of a harness. It does not pretend to be the model. It wraps whatever you attach, keeps paths inside one workspace root, and writes a plain transcript of every tool call. Free local quality tracks those weights. Subscription extras are only the hosted pieces a single disk cannot cover.
Every turn is the same four steps: plan, pick one tool, read the result, then decide whether to continue or stop. Context is trimmed each turn so a long session still fits on a laptop GPU or a strong CPU.
/v1/chat/completions endpoint on localhost or your LAN.Enough to finish a job in a folder, not a kitchen-sink plugin list. Risky calls wait for a yes.
install commands pause until you confirm the plan.stdout/stderr, so a hung command can't lock the session.No hidden vector store you cannot open. Notes live as plain markdown in the same workspace.
.md files you can open, edit, or delete like any other file.Prompts, file contents, shell output, and embeddings stay on the box you run. This page only emails a trial request. The installed agent does not phone home.
Apps in the chat are switches, not a second control panel. Live connections ship with the trial. You can also text the agent once a conversation is unlocked.
Type a task and the loop tries it: plan, tool, observe, stop. How good the answer is depends on the model you attached, because the harness is not a secret smarter model. Free local follows those weights. The subscription adds hosted reasoning, sync, and always-on text. Video generation and native video edit are the clear not-yet. Almost everything else is already in the runtime.
List, search, open, rewrite, and grep across one directory you choose. Paths cannot walk outside that root.
Markdown, JSON, CSV, HTML, Python, R, shell, SQL. Diff preview before anything stays on disk.
Shell, tests, formatters, builds, short programs. Installs and deletes wait for a yes.
Ollama, llama.cpp, LM Studio, vLLM, or any OpenAI-compatible server. The harness is the same. The brain is yours.
Every tool call lands in a local transcript. Open it like any other file. Audit what ran, in order.
Once the binary and model are on the machine, prompts and files do not go to our servers.
Mail, calendar, docs, chat, drive, and the rest of the ticker below the chat. Off means the tool is never offered.
SMS or WhatsApp, after a password check on the first message. Hosted gateway is a subscription extra so it works when the lid is closed.
Open a page you name, pull quotes, turn them into notes. With local files on: grind a folder of PDFs, CSVs, or code inside the workspace root.
Read a repo, patch a file, run the test command you approve, paste the failure back into the next turn.
Write the thing, show it, wait for send. Connected inboxes are a connector, not a default outbound pipe.
Describe, caption, and file-handle images in the workspace. Generate stills only if the attached model can. That is the model, not a hidden API.
Read CSV or Excel-like files, compute, chart to a file, write a summary. Heavy stats still want a model that can count.
Plain markdown notes plus an optional local embeddings index. You can delete a memory by deleting the file.
No native video model in the harness yet. It can organise clips on disk and write ffmpeg command plans you approve. The pixels themselves are a later problem.
A 7B or 14B on a laptop is not GPT-class reasoning. Subscription hosted extras exist for the hard turns. Files stay local unless you attach them.
Useful local models need RAM and, ideally, a GPU. Older phones and low-RAM laptops will stall.
Network fetch is off until you turn it on, and even then it is for pages you ask it to open, not a general crawler.
It can mis-scope a folder, skip a file, or write the wrong thing. Review the diff before you approve.
There is no built-in version control. Keep your own copies of anything you cannot afford to lose.
The chat on this page is a preview. It cannot see your disk. The loop starts after you install the trial.
computer.vodka is the harness. It is not "the model." If the weights are thin, the answers are thin. That is the deal on the free path.
Install it, point it at your model, work in a folder. No card. The free path is the full local loop: plan, tool, observe, approve. How well that works is how well your local or LAN model works. From the Q4 2027 public beta, hosted extras are optional and metered. Cloud reasoning for hard turns, multi-device sync, always-on text, live connectors, jobs that outlive sleep. No fixed seat fee. Quiet months stay cheap. Anything that can run on your machine stays in the local product.
No subscription · ships with the trial · quality = your model
Plan, tool, observe, stop. Read, write, search, shell, and local fetch inside the folder you choose.
Ollama, llama.cpp, LM Studio, or any OpenAI-compatible endpoint on the machine or LAN.
Markdown notes and a plain transcript. You can open or delete them without an account.
Deletes, overwrites, and installs wait for a yes. That gate does not move to the cloud.
No seat, no monthly fee, no phone-home just to keep using the agent on one computer.
Usage billed each month · no fixed fee, no send limit, only what you use
Metered hosted reasoning for the hard turns. Files stay in your workspace unless you attach them.
Sync chat and memory notes across a laptop and a phone. A single disk cannot do that by itself.
A hosted gateway so the agent can pick up SMS or chat when the laptop is closed. Bill by messages handled, not a plan cap.
Gmail, Calendar, Slack, Drive, and similar need an OAuth broker we host. You pay for the calls you make.
A hosted runner keeps a long task going after the lid closes. Local processes die with the machine.
A second person can approve a risky step and read the same transcript. That is a server product.
See tokens, connector calls, and messages for the month. Export a receipt. Stop anytime and local keeps working.
Wake the agent on a timer or an inbound event. Hosted only, because a closed laptop cannot keep a clock.
We design, build, and run the harness on our own machines in Aotearoa. Raman is in Wellington. Jayson, Ashly, and Emily are in Auckland. Each person owns a part of the runtime (loop, evals, interface, safety) and still reviews the rest.
Owns the harness loop: plan, tool call, observe, stop. Makes local models through Ollama, llama.cpp, and LM Studio feel usable on a laptop, especially Apple Silicon. Also keeps the tool runner and context trimming from grinding a long session to a halt.
Turns raw agent behavior into a task you can hand someone who does not live in a terminal. Writes evals against folders, decides what ships in a trial, and cuts anything that only looks good in a demo. Watches private-trial bugs so the Q4 2027 public beta is actually usable.
Designs the chat, the capability switches, and the approval states. Builds the desktop shell so computer.vodka feels like a modern tool instead of a raw CLI. Also owns the small details: the mark, the trial flow in the preview, and how the product reads on a phone.
Works on local notes, session logs, and the permission rules around write, delete, and install. Makes sure a bad plan cannot walk outside the folder you pointed at. If a step is hard to undo, it waits for a yes before it runs.