Low footprint
A compact process with fewer moving parts and less background overhead.
agent runner
memoria is a focused CLI agent runner with a tiny binary and a deliberately small memory footprint. Bring your Codex subscription, OpenRouter account, or OpenCode Zen/Go setup.
$ curl -fsSL https://memoria.dev/install | sh
placeholder install URL — replace with your release endpoint
$ memoria ❯ explore the project ┃gpt-6-luna | 6.8k/272k tokens (2.5%)
01 / footprint
No heavyweight runtime between you and the model. memoria stays out of the way, starts fast, and keeps system resources available for your editor, compiler, and tests.
A compact process with fewer moving parts and less background overhead.
Designed to leave memory for the work, even across long-running sessions.
One small executable. Easy to download, move, pin, and remove.
02 / in use
A real memoria session, from repository exploration to a concise project overview.
03 / compatible
Use the provider you already pay for. memoria keeps the runner consistent while the model backend stays flexible.
Connect your existing Codex subscription and start a session from the terminal.
Route across supported models with your existing OpenRouter credentials.
Use memoria with OpenCode's Zen and Go model access paths.