Research: managed-deep-agents
Cached research evidence for managed-deep-agents (not authority).
Purpose
Section titled “Purpose”Part of official langchain-ai/langchain-skills. Managed Deep Agents: deploy with CLI, SDKs, stream runs, MCP tools, React useStream UIs.
Harness Coverage
Section titled “Harness Coverage”Targets from langchain group install curated.
Trust And Risks
Section titled “Trust And Risks”trust_tier=needs-inspection; status=inspect-then-install. Official but early; persistence/checkpoint may involve state mgmt and external stores; HITL implies interactive control surfaces.
Install Prerequisites
Section titled “Install Prerequisites”Installed as part of langchain-ai/langchain-skills bundle; status=inspect-then-install.
Upstream Maintainer
Section titled “Upstream Maintainer”Comparable Alternatives
Section titled “Comparable Alternatives”Other workflow/graph libs or custom orchestration skills.
> Evidence from public web sources, GitHub (langchain-ai org Jun 2026), curated; research evidence only, not authority/endorsement.