LangChain says most of its internal agents rely on async subagents, now in deep agents
Hacubu · x · 2026-11-06
LangChain founder Harrison Chase confirms that most of the agents built inside LangChain leverage async subagents in a meaningful way, and the capability is now available in deep agents.
The quoted article "Agents Are Going Async" uses a chief-of-staff analogy: a good project manager keeps work moving after you hand it off, rather than vanishing until it's done — async subagents let the main agent dispatch long-running tasks and keep working.
Related event: LangChain Overhauls Async Subagents in Deep Agents(7 posts)→
More from coding & agent
- Late to a talk, his AI agent tapped the live transcript and took notes for him — vincent_koc · 2026-11-06
- Anthropic engineer confirms Claude Code Desktop is in the works, asks for feedback — iamsahaj_xyz · 2026-11-06
- VoidZero 十月更新:Rust 版 TypeScript 提速 8 倍,SDK 开源 — cnakazawa · 2026-11-06
- One-shot in Claude: 10-min dinosaur documentary built with Higgsfield MCP — piotrbinkowski · 2026-11-06
- Voice-to-app demo: PlaiPin device + Grok Gadget SDK builds apps without a keyboard — tetsuoai · 2026-11-06
- Wavefunction Bench Tests Coding Agents on Quantum Chemistry: Only 3 of 9 Systems Passed — CatAstro_Piyush · 2026-11-06