Ship great agents fast with our open source JS frameworks β LangChain, LangGraph, and Deep Agents. Maintained by @LangChain.
Joined January 2026
- Tweets251
- Following16
- Followers2.5K
- Likes195
@πππππππππ/πππ-ππππππππ 2.0 is out! π§΅
Using MCP with your TypeScript agents up to MCP servers just got a lot simpler: support for the latest stateless version of MCP, tools that can check in with your users when they need something, much easier auth integrations, and a ton of QoL updates.
Here's what's new π
Plus a bunch of QOL cleanup to make the adapter easier to build with:
β MultiServerMCPClient β MCPAdapter, mcpServers β servers, getTools() β listTools() (old names still work)
β Tool names carry the server name, so two servers can both expose search
β Tool errors from the server reach the model as error ToolMessages
Go try it and let us know what you think! ππππ π @πππππππππ/πππ-ππππππππ
New to MCP in LangChain? Start here: docs.langchain.com/oss/javasβ¦
Coming from 1.x? Migration guide: docs.langchain.com/oss/javasβ¦
See the release notes: github.com/langchain-ai/langβ¦
π§βπ³
Starting today, @LangChainβs Managed Deep Agents can bake your agentβs environment at deploy time. π§βπ»
No clone. No install. No repeated setup.
Drop in setup.sh or a Dockerfile. Bake once. Every new thread starts ready. π
You deploy, we provision! π€
Starting today, a @LangChain's Managed Deep Agent deploy provisions your Slack app for you π€―
No manifest. No OAuth redirects. No bot tokens to copy around.
One command, and your agent says π in Slack.
LangChain JS retweeted
An agent is 3οΈβ£ layers.
π Business logic you write.
π A harness that runs the loop.
π Infrastructure that survives production.
@hwchase17 breaks the whole stack in one video.
youtu.be/TUJmfeGTr1Q
LangChain JS retweeted
Managed Deep Agents is just getting started π
@hwchase17 just published a set for banger videos that get you up to speed how shipping production agents today looks like.
πNew YouTube playlist: Managed Deep Agents
Gives an overview of Managed Deep Agents, and then each video dives deep into core concepts.
Launching with six videos!
1β£ Intro: youtu.be/xdrB53bgpp0
2β£ Conceptual Overview: youtu.be/TUJmfeGTr1Q
3β£ Quickstart: youtu.be/L54dR9qMKzc
4β£ Instructions and Context Hub: youtu.be/8HIoZV7qlwA
5β£ Skills: youtu.be/Lhru0yMI2as
6β£ Tools: youtu.be/piBwvWgHqkY
Playlist link: youtube.com/playlist?list=PLβ¦
LangChain JS retweeted
The AI engineer's job: what it knows, what it can call, and where people reach it. π€π£οΈπ€
The rest is Managed Deep Agents.
langch.in/managed-deep-agentβ¦
LangChain JS retweeted
In Managed Deep Agents skills load in two steps, which is why a lean SKILL.md works.
The prompt keeps the name and description. The body opens when the task matches.
docs.langchain.com/langsmithβ¦
Agent skills fail when their instructions are vague and their context is bloated.
Best Practices for Creating Agent Skills is a practical guide for builders writing skills that agents can discover, load, and execute reliably.
It helps you structure skills around lean SKILL.md instructions, just-in-time references, deterministic scripts, and LLM-assisted validation instead of piling everything into one prompt.
Key features:
β’ Standard skill structure β separates core instructions, scripts, references, and reusable assets
β’ Discoverable metadata β explains naming rules and trigger-focused descriptions, including negative triggers
β’ Progressive disclosure β keeps SKILL.md under 500 lines and loads supporting context only when needed
β’ Procedural guidance β favors numbered steps, concrete templates, consistent terminology, and third-person imperative
β’ Validation workflow β covers discovery tests, logic simulation, edge-case testing, and architecture refinement
Free public GitHub repo.
Link in the reply π
LangChain JS retweeted
Mention the agent in Slack. It runs. It replies in the thread.
Managed Deep Agents treats Slack as a channel file: channels/slack.py. Mentions, DMs, and follow-ups start a run as the caller and post the answer back. No bot server to stand up either.
docs.langchain.com/langsmithβ¦
LangChain JS retweeted
You don't stand up an agent. You upload a folder.
Claude Code is a harness for your laptop. Managed Deep Agents is a harness for production.
Want Slack? Add a file. Want a daily run? Add a file. Want memory? Add a file.
LangSmith runs the harness.
docs.langchain.com/langsmithβ¦
LangChain JS retweeted
Weβre launching Managed Deep Agents today ππ
langchain.com/blog/managed-d⦠@LangChain
The goal posts for building agents have moved.
Giving an agent tools, deploying it somewhere, and putting a UI in front of it isnβt the hard part anymore.
The next challenge is everything around the agent: identity, memory, credentials, permissions, and securely connecting it to the services your users already use.
This beta release is just the beginning and our foundation what is about to come next π
LangChain JS retweeted
this blog covers 6 common workflow patterns we see with dynamic subagents (fanout and synthesize, adversarial verification, etc)
if you'd prefer to learn w/ a video, check out this excellent guide from @colifran_ with examples and trace walk throughs!
code reviews can be beautiful β€οΈ thanks @shadcn!
Plugged the new @shadcn chat components into @LangChain_JS Deep Agents and one-shotted a full code review agent.
One reviewer per file, local sandbox, streaming live. Wild how fast this was π
π§βπ» full demo: github.com/langchain-ai/streβ¦
LangChain JS retweeted
Alex recently joined the @LangChain_OSS team, and he published his first article on how Deep Agents uses prompt caching to cut API costs.
Give it a read, and give @its_ao a follow!
