managed-deepagents 0.8: memory, webhooks and sandbox files API
LangChain's managed-deepagents 0.8 brings agent and user memory with access policies, an HTTP webhook channel, Slack image and file support, OAuth options and a sandbox files API for JS and Python.

𝚖𝚊𝚗𝚊𝚐𝚎𝚍-𝚍𝚎𝚎𝚙𝚊𝚐𝚎𝚗𝚝𝚜 0.8 is here and I think it is the best thing since sliced bread things we shipped: 🧠 agent and user memory with access policies 🌐 connect webhooks with the new HTTP channel ✋ improved human-in-the-loop support 💬 Slack channels now support images and files 🔑 improved OAuth connection options 🔒 authenticate sandbox requests via a secure proxy 🔎 search the web with Parallel (thanks @p0) 📁 a runtime sandbox files API released for js and py! http://langch.in/mda