if you prefer blog format: https://blog.langchain.com/deep-agents-deploy-an-open-alternative-to-claude-managed-agents/

LangChain launched Deep Agents Deploy in beta as an open-source, model-agnostic alternative to Anthropic's Claude Managed Agents, allowing developers to deploy production-ready agents via a single deepagents deploy command with support for any model provider (OpenAI, Google, Anthropic, Ollama, and more). Unlike Claude Managed Agents—which LangChain characterizes as a "walled garden" that locks agent memory behind a proprietary API—Deep Agents Deploy is built on open standards (MCP, A2A, Agent Protocol, AGENTS.md) under an MIT license, and lets users self-host LangSmith Deployments to fully own their agent's memory and context. The key differentiation is memory ownership: because agent harnesses manage context and long-term memory, using a closed harness means accumulated agent knowledge is trapped in a vendor's infrastructure, making provider migration costly.

Deep Agents Deploy: an open alternative to Claude Managed Agents
🚀Deep Agents deploy Today we’re launching Deep Agents deploy in beta. Deep Agents deploy is the fastest way to deploy a model agnostic, ope…
With closed agent platforms like Claude Managed Agents, your agent's memory belongs to them, not you. It's locked behind their API. Agent in…
Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance …
Deep Agents deploy gets you: - Deep Agents harness - Sandbox of your choice (@daytonaio , @modal , @RunloopDev ) - Short and long term memor…
Deploy a production ready agent to the web... with the same setup you use to define a coding agent AGENTS.md - open standard /skills - open …

Source: model-releases

Related