LangChain adds browser use and async subagents to deepagents
The pairing of browser control with non-blocking subagents points toward agents that act proactively rather than only responding to prompts, a design shift worth tracking. Developers building agent workflows in Python can try both features now through the deepagents docs and compare the Stagehand approach with Playwright-based alternatives.
LangChain announced two updates to its deepagents framework in the week of the post. First, agents gained browser control through a Stagehand integration, letting them operate in a real browser on a user's behalf. Second, deepagents now supports async subagents, so the main agent stays available to the user while background tasks run. LangChain published blog posts and Python docs covering both features.
Essential reading on proactive agents ⤵️ Sydney Runkle @sydneyrunkle we've been focused on supporting more autonomous, proactive agents; here's what we shipped in deepagents this week: 1. browser use with @Stagehanddev , so your agent can work in a real browser, sometimes on your behalf! * blog: langchain.com/blog/browser-u… * deep dive: langchain.com/blog/how-we-op… * docs: docs.langchain.com/oss/python/dee… 2. async subagents, so the main agent remains available to a user while background tasks run * blog: langchain.com/blog/agents-ar… * docs: docs.langchain.com/oss/python/dee… 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 2 👀 934 ⚡
