Sign InOpen Brain
Atlas / Agent

Subagents

Open JSONConfidence: Auto-collectedLast updated 2026-09-09

Current Answer

No editorial synthesis yet — the evidence below is collected automatically from source labels. A current answer lands here once an editor approves one.

Evidence

AnthropicOfficial ReleaseOfficial Source
Claude Code ships subagents in isolated context windows
Long refactors no longer pollute the parent context — a child agent does the noisy work and reports back.
It’s Tokens All The Way Down: How RLMs are Different — Kevin Madura, AlixPartners
AI Engineer · 2026-09-09

RLMs keep large inputs in a programmable environment, letting a model inspect them with code and delegate subsets to submodels instead of attending to every token at once.

Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory
arXiv · 2026-08-17

BATON explores robot subtasks independently, stores their solutions, and manages handoffs between them, replacing multiplicative whole-task search with additive composition.

Anthropic's CCA Exam as a Field-Guide for Agentic Engineering — Frank Coyle, UC Berkeley
AI Engineer · 2026-08-08

A walkthrough of Anthropic’s architect exam doubles as a harness checklist: inspect stop reasons, narrow subagent scope, isolate outputs, and compact long-running context.

The New Primitives: Building AI Native Software — Kwindla Kramer, Daily
AI Engineer · 2026-08-07

The talk argues that agents are an early interface, not the endpoint, and demonstrates reusable primitives for AI-native software: persistent subagents, compressed context, loaded skills, generated UI, and voice.

Your Finance Agent's Bottleneck Is You — Ramana Siddanth Emani, Auditoria AI
AI Engineer · 2026-07-30

Production agent velocity depends less on model swaps than on automating the developer loop: isolate parallel work, encode workflows as skills, connect tools, and keep humans as verifiers.

Why We Killed Our Multi-Agent Pipeline — Subbiah Sethuraman and Abhilash Asokan, ZS Associates
AI Engineer · 2026-07-23

A fixed chain of specialist agents lost context and produced incoherent recommendations. The replacement separates deterministic detection, gives one agent end-to-end ownership, and uses subagents only for bounded investigations.

Gemini 3.6 Flash and Gemini 3.5 Flash-Lite are now available on AI Gateway
Vercel · 2026-07-21

Vercel AI Gateway added Gemini 3.6 Flash for coding and web work and Gemini 3.5 Flash-Lite for scoped subagent tasks, both available through AI SDK model IDs.

Agent swarms and the new model economics
Cursor · 2026-07-20

Cursor’s SQLite experiment suggests swarm harness design can matter more than model mix: separate planner and worker contexts reduced coordination churn while cheaper workers handled most tokens.

santifer/career-ops
GitHub

career-ops shows how a coding-agent harness can run personal operations: structured scoring, parallel workers, document generation, and human approval around a durable data store.

anomalyco/opencode
GitHub

OpenCode provides open-source terminal and desktop coding agents, with separate full-access and read-only modes plus a general-purpose subagent.

WorldFlowAI/everything-claude-code
GitHub

A reusable Claude Code harness bundles subagents, skills, hooks, rules, evals, and context persistence. Treat it as a pattern library to adapt, not a configuration to enable wholesale.

vastsa/PI-Desktop
GitHub

PI-Desktop packages coding agents, reviews, permissions, models, MCP, skills, and subagents into a local-first workspace, but its early-preview interfaces remain unstable.

Muse Spark 1.1 is now available on AI Gateway

Muse Spark 1.1 gives agent builders a 1M-token multimodal model with parallel tool calls, MCP support, and the option to run as a main agent or subagent.

Stable permalink · evidence auto-collected from source labels · synthesis maintained by feed7 editorial