Infrastructure kits by agent class (15)

Select an agent archetype to inspect its required jobs, Depot Picks, sourced prices, free alternatives, and failure modes.

Coding agent

Edits a repository, runs commands in a workspace, and checks the result against tests or a diff.

Gathers sources for an open-ended question and returns an answer that names those sources.

Completes a task by reading and operating a website in a browser, then stops before a consequential submit unless confirmation exists.

Operates a desktop or mobile GUI, not only a single site API, and checks that the control it used is the one it intended.

Hears or speaks on a call or a realtime channel, and confirms account-changing actions before they run.

Answers a customer from the operator's policy and escalates when sources disagree or the action is consequential.

Moves or reshapes records between files, tables, and documents, and reports rows that did not match the schema.

Answers from a retrieved corpus and says when the corpus does not support the claim.

A lead assigns subtasks to workers and accepts a result only when it matches the assignment.

Scores a trace or a patch against a rubric, without the gold label in its prompt, and records the harness version.

Runs a job on a queue or a clock, is safe to retry, and alerts when the job or its traces go dark.

Acts for one person across sessions, keeps that person's memory separate, and waits before sending or booking.

Drafts outreach from sourced fields about a person or account, and does not send until a person approves.

Reads a change or a trace for secrets, overly broad permissions, and untrusted text copied into a tool prompt. It does not produce an attack.

Runs without calling a hosted model API, using local weights, a local index, or an air-gapped serve path.