Terminal AI assistant

Switch models,
not context.

milk routes each prompt between a fast primary agent and a deep escalation agent — keeping the full conversation in sync across both. Start cheap. Go deep when you need it.

Get started View on GitHub

curl -fsSL https://raw.githubusercontent.com/scoutme/milk/main/install.sh | sh

Why milk

Automatic routing

Each prompt is classified and sent to the right agent without you changing tools.

Context handoff

When escalation fires, the primary conversation is reformatted as context — the escalation agent orients itself without a separate setup step.

Persistent memory

A Percept store survives across sessions; key facts are reinforced, decay, and promote to long-term memory over time.

Loop detection

Monitors agent output for repeating patterns, warns in the status bar, and auto-interrupts when an agent gets stuck.

Evaluation harness

Run the same scenarios against different agents and compare LLM-judged quality, tokens, cache efficiency, and latency side-by-side.

Built-in tools Streaming TUI Any backend, either role

Switch models,not context.