Milk Parlor / the gateway
Sends your model calls and returns the answers. Saves eligible request–response pairs in the background.
milkinfrastructure.com
Point OpenAI at Milk.
Keep the official SDK and your existing calls. Change two values.
# connect the OpenAI SDK to Milk Parlor
+ OPENAI_BASE_URL=https://parlor.milkinfrastructure.com/v1
+ OPENAI_API_KEY=<your Milk key>
# Responses and Chat Completions stay unchanged
your app→Milk Parlor→your model
└─ selected completed request + answer→object store→Milk Man / model tests + training
after the answer
One gateway. One agent. Saved results.
Milk Man / the agent
Give it a goal. It runs commands, starts cloud models, measures results, and saves what it learns.
Use the saved traffic to improve a model. Open a step to see what happens.
01collect
Save each eligible request and answer under your account's unique ID. Related exchanges stay grouped as one task.
02understand
Count new exchanges. At configured milestones, save a summary of topics, tasks, and response times.
03make examples
A teacher model writes new tasks inspired by the traffic. Keep training tasks separate from the tasks used to judge improvement.
04train + compare
Train an open model, tune how it runs, and compare answers, speed, and cost on the same tasks. Qwen3.5-0.8B is the first training base.
05review route
Prepare a gateway rule for the selected model. The operator reviews and signs it before customer traffic moves.
Between tasks: the heartbeat waits without model calls. A new instruction or a registered change wakes Milk Man. Closing the dashboard does not stop it.
Where do the models and data live?
Environment variables select local files or S3-compatible storage, managed inference APIs, and owned Baseten or Modal GPUs. Model files are cached separately from the runtime image. Milk Man can run locally while the data and compute stay in the cloud.
Does this guarantee a better model?
No. Milk keeps the experiment and its result, including failures. Speed improvements and better answers are different measurements. The goal is to beat a chosen baseline on your tasks, not to claim a universal ranking.
one local view
See what Milk is doing.
Saved screens from an earlier development run, not live status. The current dashboard separates chat, data, experiments, and tools.
connect an app + check status
follow the data through each job
read the agent's work
read a saved traffic summary
