start here

start using PNPM with your agents

sign up, open a project, and add PNPM to its setup script in settings → server.

Start 7-day trial with PNPM
integrationstechnologyupdated
schematic diagram of the work aldena agents do through PNPM
PNPM

pnpm ai agent: agents that install and run scripts in your workspace

add pnpm to a project's setup script and its agents install from the lockfile, run workspace scripts, and target one package with pnpm filter.

runs on
conversation sandbox
installed by
setup script
category
toolchain

pnpm is the technology that makes a monorepo tractable for an agent. installed in each conversation's sandbox it puts pnpm on the path, where every agent in the project reaches it through the bash tool.

what agents do with it

the difference between a useful agent and a slow one in a workspace is knowing what not to build. an agent with pnpm installs with pnpm install --frozen-lockfile so the tree matches the lockfile exactly, runs a script across the workspace with pnpm -r when that is genuinely what is wanted, and otherwise targets the package it changed with pnpm --filter. that keeps the feedback loop short and keeps the conversation's sandbox free for the next task.

the matching skill

pnpm ships with a skill of the same name. it carries the frozen lockfile rule, the recursive and filter flags, and the reminder that pnpm depends on node.js. skills are versioned documents that load only for the agents you assign them to, so the engineer working the monorepo carries it and the rest of the project does not.

example tasks

  • 01

    the api package fails to build. fix it without rebuilding the world.

    the agent installs from the lockfile, filters the build to the failing package, reads the compiler output, and fixes it in the conversation's sandbox.

    bashreadedit
  • 02

    add the dependency and prove nothing else broke.

    it installs the package, runs the affected workspace scripts rather than every script in the repo, and reports what changed in the lockfile.

    bashgrep

what to know before installing

the project needs a sandbox, and node.js must come earlier in the setup script. a new conversation gets its own sandbox and pnpm store, and the setup script runs on it again.

how to install PNPM

PNPM goes in the project's setup script, not once per team and not on your laptop.

  1. give the project a sandbox

    PNPM runs in each conversation's sandbox, on your team's own sandbox provider account. an owner or admin connects a provider once on the team's providers page, then picks it and a default size for the project, at creation or later in settings → server. a project with no sandbox has nowhere to run it.

  2. add it to the setup script

    settings → server holds the project's setup script, a bash script that runs once on each new sandbox, in /project, with sudo. add PNPM's install commands there and save.

  3. the next sandbox runs it

    the script runs when a conversation's sandbox is created or reused, on the conversation's first turn. settings shows the last run with its exit code and output, and a failed run leaves the sandbox usable rather than blocking the project.

  4. agents use it through bash

    from then on every agent in the project reaches PNPM with the bash tool, on the same filesystem as the checkout they are working in. the conversation's sandbox keeps it between turns, sleeping when idle and waking with the next one.

where PNPM actually lives

each conversation in a project gets its own sandbox on your team's sandbox provider account, and the project's setup script in settings → server decides what is on it. two projects never share a filesystem, so a version pinned for one client cannot collide with another's.

the sandbox provider bills its machine time to your team's account while it runs, and aldena adds nothing. the sizes are on isolated projects, and what agents may run in the sandbox is governed by the project's tool permissions.

faq

what does installing pnpm on a project give the agents?

the pnpm binary in each conversation's sandbox. agents install from the lockfile with pnpm install --frozen-lockfile, run workspace scripts with pnpm -r, and target one package with pnpm --filter, which is what makes a large monorepo workable inside a single run.

does pnpm need anything installed first?

yes, node.js. it installs through npm, so node.js has to come earlier in the project's setup script. it then enables pnpm through corepack, falling back to a global npm install if corepack is unavailable.

why does the filter flag matter to an agent?

because building an entire monorepo to check one package wastes the conversation's sandbox time and slows every answer. an agent that knows to run pnpm --filter on the package it touched gets its answer in a fraction of the time.

is there a matching skill?

yes. pnpm ships with a skill of the same name covering frozen lockfile installs, recursive scripts, filtering to one package, and the node.js dependency. skills load only for the agents you assign them to.

ready when you are

spin up your first project.

one project per client, product, or piece of work, staffed with intake, requirements, build and code review agents.