MongoDB now powers the virtual file system behind @LangChain's Deep Agents. 🚀 This new integration lets you implement Deep Agents' BackendProtocol against MongoDB Atlas instead of building your own storage layer. And agent code calling read_file, write, glob, and grep don’t have to change. Your retrieval and storage run through one backend instead of a maze of stitched-together tools. Vector, full-text, and hybrid search (via $rankFusion) route through Atlas; file reads and writes forward directly to S3. For builders of long-running or multi-agent workflows: Plans, intermediate outputs, and knowledge artifacts persist across sessions, deployments, and sub-agent handoffs, so file-based context survives between runs instead of resetting each time.

ICYMI: Everything announced at #MongoDBlocal# Build Fest is designed to help developers stay in flow and ship production AI, faster. From the new Atlas Managed MCP Server for Agents and native Atlas access inside @claudeai, Claude Code, @ChatGPT, Codex, @grok Build, @DevinAI, & @cursor_ai, to Automated Embeddings in MongoDB Atlas and @VoyageAI's voyage-code-4, plus a GA'd Embedding & Reranking API and Vector Search for Stream Processing, it's about less setup, fewer workarounds, and more time building. Get the latest: @swyx @BazeleyMikiko

"Once you have a system that can run for a month at a time, I think our relationship with computing will change pretty fast," said @jxnlco, Developer Experience Engineer at @OpenAI. "Your job is to understand what success looks like and give your models superior access to the data they need to get the job done." Liu joined MongoDB CTO, Jim Scharf, for a conversation on building production-grade AI agents. #MongoDBlocal#