LangChain launches Managed Deep Agents: build production agents as a directory of files
hwchase17 · x · 2026-10-16
LangChain announced Managed Deep Agents (MDA), a way to build and deploy production agents by writing them as a project directory of files while LangSmith runs the harness and runtime — no servers or infrastructure to manage.
- Deep Agents harness: an agent loop that plans, calls tools, manages a filesystem, and delegates to subagents.
- Managed runtime: deployments run on LangSmith Agent Server with the Agent Server API, threads, runs, streaming and an MCP endpoint out of the box.
- Structure as behavior: an agent is defined by agent.py (model, tools, middleware), instructions.md, and skills//SKILL.md files; you pick the driving model (example uses openai:gpt-5.5).
- File-aware demos: the agents can read files shared in conversations and send results back where the chat already is (e.g., turning a CSV into an iterated PowerPoint deck inside Slack), built on Slack's files API.
A practical new path for shipping multi-step agents without operating deployment infrastructure.
More from coding & agent
- Claude dev Felix Rieseberg's tutorial: 4 ways to be more ambitious with AI — daniel_mac8 · 2026-10-16
- Are the fastest GPU kernels now written by AI? Kernels are hyper-verifiable, argues one dev — fleetwood___ · 2026-10-16
- Anthropic lead engineer's 4-question prompt makes agents more ambitious, now a free skill — daniel_mac8 · 2026-10-16
- ChainForge dev shows 'feature map' for orchestrating subagents on large PRs — IanArawjo · 2026-10-16
- aiDotEngineer benchmarks agent orchestration pipelines, staging humans as Foreman and workers — vikvang1 · 2026-10-16
- Developer mass-produces 200 videos in hours using Claude Code + Hyperframes — mcraddock · 2026-10-16