LangChain

Agent-framework vendor and the fourth agent-platform maker tracked here (after anthropic, google, microsoft). Its position: agents are model + harness, and a harness is best built from composable agent-middleware, not a monolithic framework langchain-custom-harness.

What it ships

• create_agent — its minimal agent-loop builder, “the easiest way to build a custom agentic-coding-harness”; middleware stacks on top.
• Deep Agents — a production-ready harness built on create_agent (opinionated default stack).
• A library of prebuilt middleware (summarization, context editing, memory, subagents, retries, PII, human-in-the-loop, prompt caching).
• Says its own GTM and coding agents run on create_agent + tailored middleware.
• openwiki — an OSS CLI that auto-generates and maintains codebase docs for coding agents (docs-as-build-artifact); the vendor treating codebase knowledge as agent context, a facet beside its harness work.

Positioning

Where google (adk) and microsoft (Agent Framework) lead with skills as the primitive (agentskills-spec), LangChain leads with middleware as the primitive — a different decomposition of the same harness. Both reject the monolith; the question is whether the reusable unit is a loadable skill or a composable middleware (often, both). It also leans on anthropic‘s Claude Agent SDK as a comparison point (a pre-assembled middleware harness).

Related

langchain-custom-harness · agent-middleware · agentic-coding-harness · anthropic · google · microsoft