Ship great agents fast with our open source JS frameworks – LangChain, LangGraph, and Deep Agents. Maintained by @LangChain.
Joined January 2026
- Tweets251
- Following16
- Followers2.5K
- Likes195
LangChain JS retweeted
An agent is 3️⃣ layers.
👉 Business logic you write.
👉 A harness that runs the loop.
👉 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 🚀
@hwchase17 just published a set for banger videos that get you up to speed how shipping production agents today looks like.
🎓New 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!
1⃣ Intro: youtu.be/xdrB53bgpp0
2⃣ Conceptual Overview: youtu.be/TUJmfeGTr1Q
3⃣ Quickstart: youtu.be/L54dR9qMKzc
4⃣ Instructions and Context Hub: youtu.be/8HIoZV7qlwA
5⃣ Skills: youtu.be/Lhru0yMI2as
6⃣ Tools: youtu.be/piBwvWgHqkY
Playlist link: youtube.com/playlist?list=PL…
LangChain JS retweeted
The AI engineer's job: what it knows, what it can call, and where people reach it. 🤔🗣️🤝
The rest is Managed Deep Agents.
langch.in/managed-deep-agent…
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/langsmith…
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:
• Standard skill structure – separates core instructions, scripts, references, and reusable assets
• Discoverable metadata – explains naming rules and trigger-focused descriptions, including negative triggers
• Progressive disclosure – keeps SKILL.md under 500 lines and loads supporting context only when needed
• Procedural guidance – favors numbered steps, concrete templates, consistent terminology, and third-person imperative
• Validation workflow – covers discovery tests, logic simulation, edge-case testing, and architecture refinement
Free public GitHub repo.
Link in the reply 👇
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/langsmith…
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/langsmith…
LangChain JS retweeted
We’re launching Managed Deep Agents today 🎉👀
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 isn’t 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 🚀
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!
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!
LangChain JS retweeted
give Alex (@its_ao) a warm welcome to the LangChain OSS team! first article is already a banger 🔥
LangChain JS retweeted
Use GLM 5.2 today in Deep Agents Code!
docs.langchain.com/deepagent…
LangChain JS retweeted
One LangChain model object gives you access the whole @OpenRouter catalog for Deep Agents.
Route by throughput, latency, or price. Filter providers. Enforce ZDR/no data collection. Select fallback models.
When OpenRouter adds a provider or model, just pass the new slug.
docs.langchain.com/oss/pytho…
Access all the providers for GLM 5.2 in one spot.
Including one serving at over 125 TPS: openrouter.ai/z-ai/glm-5.2
LangChain JS retweeted
GLM 5.2 is already top 10 on OpenRouter this week, sitting right next to Opus 4.8.
it's also been really strong in Deep Agents across long-horizon coding, big context, tool use, and verifying work before it says it's done.
open model and much cheaper to run than its peers. On par with GPT 5.5 speed if used with @baseten (>280 TPS and <0.8s TTFT)
super easy to try for yourself: docs.langchain.com/deepagent…
We've kept hearing how GLM-5.2 beats Opus 4.8, and are skeptical of benchmarks - so we tested them on a real bug from the Cline repo. While both models fixed the issue, GLM was the winner in terms of cost and code quality:
- GLM used twice as many tokens (GLM 1.1m vs Opus 660K) but cost half as much (GLM $0.41 vs Opus $0.81)
- Opus finished quicker - 1.6 min and 12 tool calls vs GLM 4.7 min and 28 tool calls
- GLM cleaned up dead code and verified the build compiled before completing. Opus didn't - it left type errors that passed tests but broke the production build.
Both runs used the same Cline harness prompting and tools, so it seems GLM is RL trained to spend more tokens verifying its work before completing. Impressive work by the @Zai_org team!
LangChain JS retweeted
prediction: tokenomics will be the dominant theme when it comes to discussing AI adoption & usage over the course of the next 6-12 months.
org-wide token spend has come up as a point of concern in every. single. conversation i've had with customers in the past ~2 months. annual enterprise contracts with the big providers will soon begin to enter renewal, and leadership teams are already questioning whether they can justify signing at the same (& increasing) prices again.
it's no coincidence that open model adoption keeps accelerating. the cost delta between frontier APIs and running open models is widening.
this is exactly why we've been investing so heavily in model agnosticism at langchain. our frameworks (Deep Agents, LangChain, LangGraph) offer first class support for swapping providers, tools, agents, context, and traces.
when you swap models, you also shouldn't feel like you're compromising on perf. model-harness fit is very real (much like harness-task fit) -- we've been pushing hard on a model "profiles" API as a result -- check it out: docs.langchain.com/oss/pytho…
JUST IN: Microsoft is exploring DeepSeek as a cheaper alternative to OpenAI and Anthropic for Copilot Cowork. the AI model wars just got political.
the AI model wars just got political.
here’s what’s actually happening:
Microsoft is moving Copilot Cowork to usage-based pricing. the reason is brutally honest:
“We have users who do hundreds of tasks a week, which is great — they’re way productive — but the consequence is the costs can go very high.”
translation: unlimited AI is officially dead. the economics don’t work.
so Microsoft is looking for a cheaper model. and DeepSeek V4 is the option they’re exploring.
LangChain JS retweeted
open models release cadence continues to impress :)
in the past few days:
* Kimi K2.7 Code from @Kimi_Moonshot: their latest coding model, appears to do a better job at long-horizon tasks whilst improving token efficiency
* GLM 5.2 from @Zai_org: new flagship, with 1M context! up from 200K in GLM 5.1.
try them in dcode today:
docs.langchain.com/deepagent…
LangChain JS retweeted
your daily reminder that open models are plenty capable for a lot of coding work. easiest place to feel that out is deepagents! swap the model and go.
i've been enjoying GLM-5.1, Kimi K2.6, MiniMax M2.7, DeepSeek V4 Pro.
here's some examples using our CLI agent in headless mode
