LangChain launches Managed Deep Agents for serverless deployment
hwchase17 · x · 2026-08-19
LangChain released Managed Deep Agents (MDA), a solution to simplify the building and deployment of production-grade agents.
Key Features:
- Serverless Architecture: Developers write business logic (instructions, tools, skills), while MDA handles the underlying harness and runtime.
- Deep Agents Harness: Provides the agent loop, including planning, tool calling, filesystem management, and delegation to subagents.
- Managed Runtime: Hosted by LangSmith Deployment to maintain session state across restarts.
Workflow:
Agents are organized as project folders containing agent.py, instructions.md, and skills, with support for middleware and MCP connectors.
More from coding & agent
- Train AI Models Locally via Desktop App, Connect Claude Code with One Command — Saboo_Shubham_ · 2026-08-19
- Stop Letting Your Agents Ship Ugly UIs: A Practical Design Guide for AI Apps — nutlope · 2026-08-19
- ByteDance Releases StartupBench: Top Models Complete Only 30% of Tasks — ByteDance-Seed · 2026-08-19
- Agentic ESOpt: Fine-Tuning Long-Horizon Agents with Minimal GPU Requirements — NationalUniversityofSingapore · 2026-08-19
- RUPA: Improving Agent Reliability via Relational Uncertainty Propagation — ICIP · 2026-08-19
- stdio-supervisor: Fixes MCP Server Orphaned Process Leaks — ItsDeadWeight · 2026-08-19