---
schema: 1
type: term
title: agent swarms
description: >-
  **Agent swarms** — as used in this channel's material — is Anthropic's feature
  for running many sub-agents in parallel. Kieran Claassen reported his `/LFG`
  command dropped from 20 minutes to 5 with agent swarms enabled; his caveat was
  that swarms shine in **implementation** (where the plan and dependency graph
  are clear), less so in planning phases where research needs refinement rather
  than breadth.
canonical: 'https://liquidgold.cc/channel/everyinc/explore/term/agent-swarms-9b7b989821a1'
markdown: >-
  https://liquidgold.cc/channel/everyinc/explore/term/agent-swarms-9b7b989821a1.md
llms: null
parent: 'https://liquidgold.cc/channel/everyinc/llms.txt'
channel: everyinc
updated: '2026-10-23T22:12:35.346Z'
language: null
children: []
---


# agent swarms

Canonical: https://liquidgold.cc/channel/everyinc/explore/term/agent-swarms-9b7b989821a1

Parent: [Channel index](https://liquidgold.cc/channel/everyinc/llms.txt)

## Definition

**Agent swarms** — as used in this channel's material — is Anthropic's feature for running many sub-agents in parallel. Kieran Claassen reported his `/LFG` command dropped from 20 minutes to 5 with agent swarms enabled; his caveat was that swarms shine in **implementation** (where the plan and dependency graph are clear), less so in planning phases where research needs refinement rather than breadth.

<Section title=“What this term means here”>In this channel's material, **agent swarms** refers to Anthropic's feature for running many sub-agents in parallel — an extension of the parallel sub-agents that Opus 4.6 already spawns by default for research, code exploration, and knowledge-work tasks. The clearest evidence comes from Kieran Claassen, whose compound engineering workflow depends on parallelism: with Anthropic's agent swarms enabled, his `/LFG` command dropped from 20 minutes to 5.</Section><Section title=“Where swarms help — and where they don't”>Kieran's key caveat scopes the term precisely: swarms shine in **implementation**, where the plan and dependency graph are already clear and work can be split across agents. In **planning** phases, by contrast, research needs refinement rather than breadth, and parallel agents add less value.</Section><Section title=“Swarm in context”>Agent swarms sit alongside related parallelism behavior in the channel's coverage: Opus 4.6 parallelizes by default, aggressively spawning parallel sub-agents (which Naveen described as the model being “hungry for context”), while Codex only has sub-agents in experimental mode. Agent swarms are Anthropic's packaged version of that parallelism — and in the team's testing, parallelism emerged as one of the real differentiators between the two labs' coding agents.</Section>