LangChain launches Managed Deep Agents: define agents as a directory of files
hwchase17 · x · 2026-11-03
LangChain released Managed Deep Agents (MDA), positioned as the simplest way to build and deploy production agents: you write the agent's intelligence while LangSmith runs the harness and runtime — no servers, no infrastructure.
Core components:
- Deep Agents harness: agent loop that plans, calls tools, manages a filesystem, and delegates to subagents
- Managed runtime: deployments run on LangSmith Agent Server with Agent Server API, threads, runs, streaming, and an MCP endpoint
An agent is defined as a project directory: model & config, instructions.md, skills/ (e.g., research/SKILL.md), tools, middleware, and MCP connectors — e.g. definedeepagent(name="research-assistant", model="openai:gpt-5.5", tools=[...], middleware=[...]).
LangChain founder hwchase17 amplified the announcement.
More from coding & agent
- NVIDIA open-sources Auto Ontology, a semantic layer to stop AI agents querying the wrong data — DrDatta_AIIMS · 2026-11-03
- NorthCUA: experience flywheel pushes open-source computer-use agents to SOTA — beipo-ai · 2026-11-03
- Miles Brundage: Claude Code has gotten pushy with suggested follow-up projects — Miles_Brundage · 2026-11-03
- 10 open-source repos to automate work with AI agents, n8n leads with 267k stars — victor_explore · 2026-11-03
- Open-source pipeline turns one prompt into a full animated reel — free, no video-gen APIs — _haiderfarooq · 2026-11-03
- Open-Source MCP Server Demo Hooks Custom Tools into OpenAI via Cloudflare Tunnels — modelcontextprotocol · 2026-11-03