LangChain details two context modes for subagents: isolated vs forked
LangChain · x · 2026-09-09
LangChain published "Organizing Context in a Multi-Agent Harness," tackling the hardest part of subagent design: deciding what context to pass in and what to return.
The guide covers two input context modes now supported:
- Isolated: the subagent gets a completely new prompt with no inherited history — best for context isolation and parallel reasoning.
- Forked: the subagent starts exactly where the main agent left off, with a copy of the full message history — best for tasks needing continuity.
It also explains when to use each mode, noting subagents excel at parallelizing work and delegating to specialized agents but are sensitive to context design.
Related event: LangChain Deep Agents Let Subagents Fork Full Context(4 posts)→
More from coding & agent
- The AI code quality paradox: maintainability up 3.8% while change confidence falls 6.1% — rseroter · 2026-09-09
- OpenClaw 2.0 uses multiplayer agents to triage and review community PRs — heyneighbor · 2026-09-09
- Meta launches Muse, a personal AI agent, with a deep dive on its safety design — AIatMeta · 2026-09-09
- Nous Research's Hermes gets first-class support in DHH's agentic Linux distro Omarchy — NousResearch · 2026-09-09
- Moonshot's 24/7 always-listening agent opens 100 beta spots, immediately facing 'show a real output' skepticism — nikola_mr64990 · 2026-09-09
- Meta details Muse agent safety: isolated VMs and a Sentinel gatekeeper for every outbound action — alexandr_wang · 2026-09-09