LangChain Launches Managed Deep Agents: Deploy Production Agents as a Directory of Files
LangChain · x · 2026-10-07
LangChain has launched Managed Deep Agents (MDA): build an agent as a project directory of files and LangSmith runs the harness and runtime—no servers or infrastructure to wire up.
- Developers write only the intelligence: instructions.md, skills (SKILL.md files), tools, middleware, MCP connectors, and pick the driving model
- The Deep Agents harness handles the loop: planning, tool calls, filesystem management, and subagent delegation
- The managed runtime provides the Agent Server API, threads, runs, streaming, and an MCP endpoint out of the box
Positioned as the simplest way to build and deploy production agents; docs are live.
More from coding & agent
- Coinbase's Lincoln Murr on paying AI agents via the x402 protocol — MurrLincoln · 2026-10-07
- Resend logs 3M MCP calls last month, up ~30x since April — dsp_ · 2026-10-07
- Dev vibes-clones his 2-year game with Claude: looks right, plays wrong — IanArawjo · 2026-10-07
- Y Combinator-backed Linc launches discovery layer that turns enterprise tribal knowledge into SOPs — ycombinator · 2026-10-07
- Don't delete your agent memory systems yet: focused .md files still win — gregbarbosa · 2026-10-07
- A no-RAG agent memory system with plain markdown saves ~155k tokens per run — gregbarbosa · 2026-10-07