LangChain ships Managed Deep Agents, evolving from LangSmith Deployment into a full agent runtime
hwchase17 · x · 2026-09-14
LangChain founder Harrison Chase shares an overview of the managed agents landscape and introduces Managed Deep Agents (MDA).
- LangChain shipped its first managed agent product, LangSmith Deployment (LSD), two years ago — a self-hostable runtime now hosting everything from LangGraph workflows to deepagents-based apps
- MDA lets devs bring the agent's intelligence (instructions, skills, tools, model) while the platform provides the Deep Agents harness (planning, tool calls, filesystem, subagent delegation) and a managed runtime with session and credential management
- Chase's thesis: managed deployment was step one; the next step is a complete foundation so devs don't assemble it themselves
Docs show agents organized as project folders with agent.py, instructions.md and a skills directory.
More from coding & agent
- Complete beginner's guide to Codex with GPT-6 Astra covers 28 essentials — iamrobotbear · 2026-09-15
- Nimble launches self-learning web research agents that build structured datasets — Shruti_0810 · 2026-09-15
- Microsoft previews MulticloudDB SDK: one Java API across Cosmos DB, DynamoDB and Spanner — adnan_hashmi · 2026-09-15
- Developer builds full Three.js website prototype in 5 hours with GPT-6 Astra — techartist_ · 2026-09-15
- One image, one agent: GPT-6 Astra + HYPER3D MCP auto-builds 3D scenes — SarahAnnabels · 2026-09-15
- Bolt.new trains open-weight models on user sessions, paid teams can opt out — testingcatalog · 2026-09-15