LangChain(@LangChainAI)

An inside look from @nickhollon10 ⤵️

LangChain (@LangChain) — Thu, 23 Jul 2026 17:04:02 GMT

An inside look from @nickhollon10 ⤵️

LangChain OSS@LangChain_OSS

x.com/i/article/2080…

🔗 View Quoted Tweet

💬0🔄0❤️7👀1975📊1

⚡ Powered by xgo.ing

.@sydneyrunkle on the common applications for Deep Agents.

LangChain (@LangChain) — Thu, 23 Jul 2026 16:02:40 GMT

.@sydneyrunkle on the common applications for Deep Agents.

Your browser does not support the video tag.

🔗 View on Twitter

💬2🔄1❤️12👀2503📊4

⚡ Powered by xgo.ing

@sydneyrunkle See more in our Deep Agents Fireside Chat. https://t.co/m786bqcCgf

LangChain (@LangChain) — Thu, 23 Jul 2026 16:02:40 GMT

@sydneyrunkle See more in our Deep Agents Fireside Chat. 
youtu.be/GbzEDgcuGJU

💬0🔄2❤️5👀846📊1

⚡ Powered by xgo.ing

Agent governance extends beyond security, bringing together authentication, audit logs, user managem...

LangChain (@LangChain) — Thu, 23 Jul 2026 15:00:00 GMT

Agent governance extends beyond security, bringing together authentication, audit logs, user management, provider secrets, data separation, data residency, rate limits, fallbacks, and centralized spend controls.

In Building Governed Agents, we’ll share a practical framework for evaluating these requirements across cost, compliance, and operational scale, along with the infrastructure teams need as agents move from experimentation into production.

Save your spot: events.langchain.com/register/build…

💬8🔄3❤️26👀3253📊11

⚡ Powered by xgo.ing

Watch the full fireside chat between @hwchase17 + Jensen Huang. https://t.co/7lgFJSQa85

LangChain (@LangChain) — Thu, 23 Jul 2026 13:02:22 GMT

Watch the full fireside chat between @hwchase17 + Jensen Huang.
youtube.com/watch?v=Yy3JH6…

💬0🔄2❤️3👀2501📊1

⚡ Powered by xgo.ing

Lower inference costs makes running and evaluating more specialized agents in production more practi...

LangChain (@LangChain) — Thu, 23 Jul 2026 13:02:21 GMT

Lower inference costs makes running and evaluating more specialized agents in production more practical. 

Teams can create agents for specific domains, use evals and traces to measure performance, and adapt the harness as their workflows change.

Your browser does not support the video tag.

🔗 View on Twitter

💬6🔄0❤️31👀4495📊9

⚡ Powered by xgo.ing

The difference between an agent that works once and one that keeps improving often comes down to the...

LangChain (@LangChain) — Wed, 22 Jul 2026 21:00:40 GMT

The difference between an agent that works once and one that keeps improving often comes down to the loops around it, including how it checks its work, responds to new inputs, and turns production traces into better prompts, tools, graders, and configurations.

Join us for The Art Of Loop Engineering to learn how these loops fit together, where human oversight matters most, and how LangChain and LangSmith support the full improvement cycle.

Register before the session: events.langchain.com/webinar/the-ar…

💬8🔄7❤️57👀7789📊20

⚡ Powered by xgo.ing

We’re hosting a meetup with @cognition on Tuesday. Come learn about LLM Wikis and how to give your ...

LangChain (@LangChain) — Wed, 22 Jul 2026 19:52:27 GMT

We’re hosting a meetup with @cognition on Tuesday.

Come learn about LLM Wikis and how to give your agents open memory with OpenWiki.

RSVP while spaces last: luma.com/mylwoabu

💬0🔄3❤️26👀7608📊5

⚡ Powered by xgo.ing

Join us at Interrupt London on October 13th! 🎙️ @hwchase17, @jpmorgan, @useapolloio, @modal, and mo...

LangChain (@LangChain) — Wed, 22 Jul 2026 19:00:01 GMT

Join us at Interrupt London on October 13th!
🎙️ @hwchase17, @jpmorgan, @useapolloio, @modal, and more
💻 Technical sessions + hands-on workshops
🤝 Networking with other agent builders

🎟️ Tickets are limited. Save your spotinterrupt.langchain.com/nyc7Rub

💬1🔄3❤️12👀7856📊3

⚡ Powered by xgo.ing

Available today in the langchain-ai/langchain-skills repo: https://t.co/P3AOjCZPjV 💻 Install in Co...

LangChain (@LangChain) — Wed, 22 Jul 2026 17:59:06 GMT

Available today in the langchain-ai/langchain-skills repo: github.com/langchain-ai/l…

💻 Install in Codex or Claude Code, open the repo w/ the agent you want to evaluate, start with a prompt

✨ Get a @Harborframework task under evals/, an actual target run, and a review of whether the verifier measured the intended behavior correctly.

Viv@Vtrivedy10

x.com/i/article/2079…

🔗 View Quoted Tweet

💬11🔄24❤️244👀30859📊67

⚡ Powered by xgo.ing

We’re launching the Eval Engineering Skill, a skill that helps coding agents build evals using conte...

LangChain (@LangChain) — Wed, 22 Jul 2026 17:08:39 GMT

We’re launching the Eval Engineering Skill, a skill that helps coding agents build evals using context from a repository + agent traces.

Everything you need to know from @vtrivedy10 ⤵️

Viv@Vtrivedy10

x.com/i/article/2079…

🔗 View Quoted Tweet

💬14🔄31❤️331👀46909📊102

⚡ Powered by xgo.ing

Every turn of a conversation has two pieces. 👤 What the user did: observable signals that tell you ...

LangChain (@LangChain) — Wed, 22 Jul 2026 16:02:41 GMT

Every turn of a conversation has two pieces.
👤 What the user did: observable signals that tell you where the conversation is
🤖 What the agent did: controllable inputs that condition where it goes next

@GetCandidly's IO-HMM keeps these separate by design. 
👤 User behavior reads the state
🤖 Agent behavior shifts it

💬5🔄7❤️50👀8201📊14

⚡ Powered by xgo.ing

@getcandidly Full story: https://t.co/mTxacVG2hI

LangChain (@LangChain) — Wed, 22 Jul 2026 16:02:41 GMT

@getcandidly Full story: langchain.com/blog/how-candi…

💬1🔄1❤️5👀1741📊2

⚡ Powered by xgo.ing

.@its_ao added native browser control to dcode with one /goal. Here’s how you can use /goal to do...

LangChain (@LangChain) — Wed, 22 Jul 2026 15:01:21 GMT

.@its_ao added native browser control to dcode with one /goal.  

Here’s how you can use /goal to do the same: docs.langchain.com/oss/python/dee…

Your browser does not support the video tag.

🔗 View on Twitter

💬4🔄5❤️43👀10242📊11

⚡ Powered by xgo.ing

Interrupt, The Agent Conference by LangChain returns this fall: 📍NYC: September 24 📍London: Octob...

LangChain (@LangChain) — Wed, 22 Jul 2026 14:05:32 GMT

Interrupt, The Agent Conference by LangChain returns this fall:
📍NYC: September 24 
📍London: October 13  

Get more info + save your seat while spaces last ainterrupt.langchain.com1O

LangChain@LangChain

At Interrupt, we learned how LinkedIn cut time-to-interview by 60% By building a hiring agent with LangGraph.  

Watch the full session: youtu.be/LUemJGG2k4c

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬1🔄3❤️36👀8206📊5

⚡ Powered by xgo.ing

At Interrupt, we learned how LinkedIn cut time-to-interview by 60% By building a hiring agent with L...

LangChain (@LangChain) — Wed, 22 Jul 2026 13:36:00 GMT

At Interrupt, we learned how LinkedIn cut time-to-interview by 60% By building a hiring agent with LangGraph.  

Watch the full session: youtu.be/LUemJGG2k4c

Your browser does not support the video tag.

🔗 View on Twitter

💬4🔄5❤️58👀13222📊14

⚡ Powered by xgo.ing

"Graph engineering" is having a moment, but it's not a new thing! We've been building agents powere...

LangChain (@LangChain) — Wed, 22 Jul 2026 12:26:25 GMT

"Graph engineering" is having a moment, but it's not a new thing!

We've been building agents powered by graphs for three years, here's what we've learned!

Sydney Runkle@sydneyrunkle

x.com/i/article/2079…

🔗 View Quoted Tweet

💬8🔄20❤️153👀25093📊40

⚡ Powered by xgo.ing

.@useapolloio cut dev-to-launch work for new AI Assistant skills by 80-85%, by tearing out a hand-wi...

LangChain (@LangChain) — Tue, 21 Jul 2026 19:00:17 GMT

.@useapolloio cut dev-to-launch work for new AI Assistant skills by 80-85%, by tearing out a hand-wired supervisor for Deep Agents.

Full story: langchain.com/blog/how-apoll…

💬4🔄4❤️38👀8508📊12

⚡ Powered by xgo.ing

🎧 Full audio on your traces ⚡ STT/TTS latency 🗣️ interruptions + VAD Only a few lines of code t...

LangChain (@LangChain) — Tue, 21 Jul 2026 17:11:43 GMT

🎧 Full audio on your traces

⚡ STT/TTS latency

🗣️ interruptions + VAD

Only a few lines of code to set up👇

LangChain@LangChain

Voice agents are exploding. Don’t let them be a black box in production.

Today, we’re launching LangSmith tracing for 4 voice frameworks:
🎙️ @pipecat_ai
🎙️ @livekit
🎙️ @OpenAI Realtime
🎙️ @GeminiApp Live (Google ADK)

Learn molangchain.com/blog/trace-voi…Fkmj

🔗 View Quoted Tweet

💬1🔄5❤️37👀9675📊7

⚡ Powered by xgo.ing

Google Gemini AI Studio, Enterprise Vertex and the new Gemini 3.6 Flash, and 3.5 Flash Lite now avai...

LangChain (@LangChain) — Tue, 21 Jul 2026 17:08:22 GMT

Google Gemini AI Studio, Enterprise Vertex and the new Gemini 3.6 Flash, and 3.5 Flash Lite now available in OpenWiki

Brace@BraceSproul

OpenWiki now supports Gemini AI Studio & Enterprise Vertex AI!

This change also adds the new Gemini 3.6 Flash and 3.5 Flash Lite (released today)

Big thank you to @bradhuffman and @sadrig91 for contributing these two PRs!

Try it out today, it's fully OSS and the easiest way to generate and maintain codebase documentation 👇

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬1🔄4❤️27👀8367📊5

⚡ Powered by xgo.ing

Voice agents are exploding. Don’t let them be a black box in production. Today, we’re launching Lan...

LangChain (@LangChain) — Tue, 21 Jul 2026 16:45:09 GMT

Voice agents are exploding. Don’t let them be a black box in production.

Today, we’re launching LangSmith tracing for 4 voice frameworks:
🎙️ @pipecat_ai
🎙️ @livekit
🎙️ @OpenAI Realtime
🎙️ @GeminiApp Live (Google ADK)

Learn molangchain.com/blog/trace-voi…Fkmj

💬9🔄10❤️61👀29915📊24

⚡ Powered by xgo.ing

We built a tracing plugin that turns every @cursor_ai agent session into a structured trace in LangS...

LangChain (@LangChain) — Tue, 21 Jul 2026 15:00:00 GMT

We built a tracing plugin that turns every @cursor_ai agent session into a structured trace in LangSmith: the model run, every tool call underneath it, and any nested subagent work. 

Attachments get recovered and rendered inline too.

This is the third video in our coding-agent tracing series (Claude Code, Codex, Cursor). All three share the same trace schema, so you can compare them in one place.

Your browser does not support the video tag.

🔗 View on Twitter

💬8🔄7❤️52👀8548📊19

⚡ Powered by xgo.ing

"Once you've found the shape of intelligence, you know what it looks like." @enoreyes from @factor...

LangChain (@LangChain) — Tue, 21 Jul 2026 14:02:19 GMT

"Once you've found the shape of intelligence, you know what it looks like." 

@enoreyes from @factoryAI on why he thinks distillation is basically unstoppable and why model labs might already know it.

Your browser does not support the video tag.

🔗 View on Twitter

💬6🔄4❤️39👀8287📊13

⚡ Powered by xgo.ing

@EnoReyes @FactoryAI Watch the full conversation on the Max Agency podcast: ⏯️ YouTube: https://t.c...

LangChain (@LangChain) — Tue, 21 Jul 2026 14:02:19 GMT

@EnoReyes@FactoryAI Watch the full conversation on the Max Agency podcast:

⏯️ YouTube: youtube.com/watch?v=HbUznY… 

🎧 Apple:podcasts.apple.com/us/podcast/the…H 

🎧 Spotifyopen.spotify.com/episode/5CkX1d…dj

💬0🔄0❤️3👀2839📊1

⚡ Powered by xgo.ing

Interrupt, The Agent Conference by LangChain returns this fall with two new stops: 📍NYC: September ...

LangChain (@LangChain) — Tue, 21 Jul 2026 12:52:10 GMT

Interrupt, The Agent Conference by LangChain returns this fall with two new stops:
📍NYC: September 24
📍London: October 13

Get more information about Interrupt + save your seat while spaces last ainterrupt.langchain.comxf

Your browser does not support the video tag.

🔗 View on Twitter

💬2🔄7❤️35👀8471📊8

⚡ Powered by xgo.ing

The Agent Development Lifecycle is continuous building, deploying, monitoring, improving, and govern...

LangChain (@LangChain) — Mon, 20 Jul 2026 20:46:26 GMT

The Agent Development Lifecycle is continuous building, deploying, monitoring, improving, and governing agents as they move into production.

Join the next sessions in Build More with LangSmith: Summer AMA Series to learn how LangSmith supports more of that lifecycle:

✅ July 23 — Build More with LangSmith Fleet
✅  July 30 — Build More with LangSmith Insights

Explore the series and save your spot: events.langchain.com/ama-series/bui…

💬4🔄2❤️39👀8167📊9

⚡ Powered by xgo.ing

IssueBench is a detailed evaluation suite we built for Engine (continual learning agent in LangSmith...

LangChain (@LangChain) — Mon, 20 Jul 2026 17:09:44 GMT

IssueBench is a detailed evaluation suite we built for Engine (continual learning agent in LangSmith, runs on your traces, automatically improves your agent)

Evaluating Engine was a tricky problem due to the type of data it needs to run on, so we wrote this blog outlining what the benchmark is, and how we made it:

Brace@BraceSproul

x.com/i/article/2079…

🔗 View Quoted Tweet

💬3🔄4❤️41👀8450📊8

⚡ Powered by xgo.ing

Governing agents requires teams to think across the full system, from authentication, audit logs, ra...

LangChain (@LangChain) — Mon, 20 Jul 2026 16:19:24 GMT

Governing agents requires teams to think across the full system, from authentication, audit logs, rate limits, fallbacks, and centralized spend controls.

Our latest conceptual guide breaks down the foundations teams need.

langchain.com/blog/building-…

💬2🔄7❤️55👀8081📊14

⚡ Powered by xgo.ing

We’re making LangSmith Sandboxes available to try for free. Start today: https://t.co/arJLavvyXM

LangChain (@LangChain) — Mon, 20 Jul 2026 15:01:24 GMT

We’re making LangSmith Sandboxes available to try for free.

Start today: smith.langchain.com

Your browser does not support the video tag.

🔗 View on Twitter

💬12🔄18❤️133👀13901📊37

⚡ Powered by xgo.ing

Deep Agents explained in one sentence by @sydneyrunkle

LangChain (@LangChain) — Mon, 20 Jul 2026 14:01:47 GMT

Deep Agents explained in one sentence by @sydneyrunkle

Your browser does not support the video tag.

🔗 View on Twitter

💬2🔄2❤️38👀10743📊7

⚡ Powered by xgo.ing

@sydneyrunkle See more in our Deep Agents Fireside Chat. https://t.co/m786bqcCgf

LangChain (@LangChain) — Mon, 20 Jul 2026 14:01:47 GMT

@sydneyrunkle See more in our Deep Agents Fireside Chat. 
youtu.be/GbzEDgcuGJU

💬0🔄0❤️3👀3086📊1

⚡ Powered by xgo.ing

Interrupt returns this fall! 📍 NYC: September 24 📍 London: October 13 Info + RSVP: https://t.co...

LangChain (@LangChain) — Mon, 20 Jul 2026 13:14:41 GMT

Interrupt returns this fall!
📍 NYC: September 24 
📍 London: October 13 

Info + RSVPinterrupt.langchain.comxf

LangChain@LangChain

At Interrupt, @Coinbase Engineering Manager Evan Kormos took the stage to share how their developer support team built a self-improving agentic system on top of self-hosted LangSmith.   

Full session: youtu.be/py9d6zTl4Dc

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬1🔄6❤️26👀9038📊6

⚡ Powered by xgo.ing

At Interrupt, @Coinbase Engineering Manager Evan Kormos took the stage to share how their developer ...

LangChain (@LangChain) — Mon, 20 Jul 2026 13:00:02 GMT

At Interrupt, @Coinbase Engineering Manager Evan Kormos took the stage to share how their developer support team built a self-improving agentic system on top of self-hosted LangSmith.   

Full session: youtu.be/py9d6zTl4Dc

Your browser does not support the video tag.

🔗 View on Twitter

💬5🔄10❤️75👀19796📊23

⚡ Powered by xgo.ing

We've built a full software engineering agent factory in house, and open-sourced every piece of it. ...

LangChain (@LangChain) — Sat, 18 Jul 2026 19:14:54 GMT

We've built a full software engineering agent factory in house, and open-sourced every piece of it. @BraceSproul's blog dives into each of those components, what they're used for, and why them being OSS matters

Brace@BraceSproul

x.com/i/article/2078…

🔗 View Quoted Tweet

💬16🔄55❤️518👀109873📊155

⚡ Powered by xgo.ing

GPT Researcher, built on deepagents, is the easiest way to get started building a deep research agen...

LangChain (@LangChain) — Sat, 18 Jul 2026 14:26:42 GMT

GPT Researcher, built on deepagents, is the easiest way to get started building a deep research agent!

Sydney Runkle@sydneyrunkle

GPT Researcher from @assaf_elovic and @tavilyai is a high-performance, open-source deep research implementation (almost at 30k ⭐), now built on @LangChain's Deep Agents.

It uses the same plan → parallel research → review → publish pipeline as the original LangGraph implementation, but with far less code: planning, delegation & context management are emergent in the harness rather than hardcoded in the graph.

Swapping GPT researcher in for tavily web search gives ~2x the verified citations at equal-or-better quality, with GPT-researcher winning in 7/10 Deep Research Bench tasks!

github.com/assafelovic/gp…

🔗 View Quoted Tweet

💬5🔄7❤️91👀30561📊21

⚡ Powered by xgo.ing

LangChain is hiring. Check out our open roles and apply https://t.co/xJOcm9utQU

LangChain (@LangChain) — Fri, 17 Jul 2026 21:05:03 GMT

LangChain is hiring.

Check out our open roles and apply
langchain.com/careers

💬0🔄0❤️4👀3137📊1

⚡ Powered by xgo.ing

This agent turns an RFP into a fully drafted response, citations included, letting the SME review st...

LangChain (@LangChain) — Fri, 17 Jul 2026 20:01:00 GMT

This agent turns an RFP into a fully drafted response, citations included, letting the SME review start from a draft instead of a blank page.

1️⃣ Requirements extraction agent: Pulls scope, SLAs, pricing format, + regulatory provisions from RFP package
2️⃣ Content mapping agent: Matches requirements to approved internal content
3️⃣ Draft generation agent: Writes responses with citations
4️⃣ Gap detection agent: Flags exactly what needs a human

Built with LangGraph + LangSmith, measured with @payicorp. langchain.com/blog/proving-t…

💬4🔄4❤️38👀8417📊12

⚡ Powered by xgo.ing

👀

LangChain (@LangChain) — Fri, 17 Jul 2026 19:58:10 GMT

👀

Brace@BraceSproul

i need to hire someone who's really really good at evals and benchmarks in SF (or maybe nyc if you're super special)

if this is you, or you know someone who fits this, please dm me! i'd love to chat

🔗 View Quoted Tweet

💬2🔄3❤️15👀13496📊3

⚡ Powered by xgo.ing

In 40 minutes, @sydneyrunkle and @jakebroekhuizen run through everything you need to know about Deep...

LangChain (@LangChain) — Fri, 17 Jul 2026 19:00:01 GMT

In 40 minutes, @sydneyrunkle and @jakebroekhuizen run through everything you need to know about Deep Agents.

What are Deep Agents?
How do they work?
What are some of the most common use cases?
What are the core components?
How do file systems work?

Watch the full session ⤵️

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄12❤️79👀12242📊23

⚡ Powered by xgo.ing

Agents are a new kind of software: endless inputs, non-deterministic outputs Build them like normal...

LangChain (@LangChain) — Fri, 17 Jul 2026 17:00:01 GMT

Agents are a new kind of software: endless inputs, non-deterministic outputs

Build them like normal software and they break

We built LangSmith around the Agent Development Lifecycle:

Build → Test → Deploy → Monitor

The lifecycle explained ⤵️

Your browser does not support the video tag.

🔗 View on Twitter

💬5🔄15❤️123👀14837📊32

⚡ Powered by xgo.ing

On July 23rd, @sydneyrunkle will break down how teams can use agent, verification, event-driven, and...

LangChain (@LangChain) — Fri, 17 Jul 2026 15:01:15 GMT

On July 23rd, @sydneyrunkle will break down how teams can use agent, verification, event-driven, and hill-climbing loops to build systems that are more observable, testable, and dependable over time.

Save your spot: events.langchain.com/webinar/the-ar…

💬2🔄0❤️35👀6210📊8

⚡ Powered by xgo.ing

@AbridgeHQ Interrupt returns this fall 📍 NYC: September 24 📍 London: October 13 Save your spot ⤵...

LangChain (@LangChain) — Fri, 17 Jul 2026 12:45:22 GMT

@AbridgeHQ Interrupt returns this fall
📍 NYC: September 24
📍 London: October 13

Save your spot ⤵️interrupt.langchain.comxf

💬0🔄1❤️2👀2529📊1

⚡ Powered by xgo.ing

"Trust is earned in drops, but lost in buckets.” @AbridgeHQ's VP of Product Janie Lee on what it ac...

LangChain (@LangChain) — Fri, 17 Jul 2026 12:45:21 GMT

"Trust is earned in drops, but lost in buckets.”

@AbridgeHQ's VP of Product Janie Lee on what it actually takes to ship AI in clinical settings.

Watch the full Interrupt keynote: youtu.be/mxweSHetuN8

Your browser does not support the video tag.

🔗 View on Twitter

💬3🔄6❤️57👀10022📊15

⚡ Powered by xgo.ing

We’re hosting a meetup with @cognition on July 28th. Come learn about LLM Wikis and how to give you...

LangChain (@LangChain) — Thu, 16 Jul 2026 21:04:48 GMT

We’re hosting a meetup with @cognition on July 28th.

Come learn about LLM Wikis and how to give your agents open memory with OpenWiki.

RSVP while spaces last: luma.com/mylwoabu

💬2🔄2❤️26👀5896📊5

⚡ Powered by xgo.ing

As agents take on larger workloads across the organization, governance becomes part of the system de...

LangChain (@LangChain) — Thu, 16 Jul 2026 19:26:40 GMT

As agents take on larger workloads across the organization, governance becomes part of the system design, shaping how teams control spend, protect sensitive data, enforce internal policies, and manage access at scale.

On August 12th, we’ll break down the foundations teams need to govern production agents and where gateway infrastructure fits into the broader Agent Development Lifecycle.

events.langchain.com/register/build…

💬1🔄2❤️38👀5591📊6

⚡ Powered by xgo.ing

OpenWiki is adopting OKF in 0.2! OKF will lay the ground work for a lot of new exciting features an...

LangChain (@LangChain) — Thu, 16 Jul 2026 16:59:34 GMT

OpenWiki is adopting OKF in 0.2!

OKF will lay the ground work for a lot of new exciting features and capabilities in OpenWiki, and it'll allow us to take advantage of the growing OSS ecosystem around OKF!

Checkout @BraceSproul's short blog on what this means for OpenWiki, and its users:

Brace@BraceSproul

x.com/i/article/2077…

🔗 View Quoted Tweet

💬6🔄9❤️116👀17294📊24

⚡ Powered by xgo.ing

New video from @its_ao. How to run @NVIDIA Nemotron 3 Ultra with @baseten + Deep Agents Code. ✅ 5...

LangChain (@LangChain) — Thu, 16 Jul 2026 15:00:03 GMT

New video from @its_ao. 

How to run @NVIDIA Nemotron 3 Ultra with @baseten + Deep Agents Code.

✅ 550B parameters, up to 300 tokens per second
✅ Terminal agent w/ skills, sub-agents, MCP support
✅ First-class tracing through LangSmith

Your browser does not support the video tag.

🔗 View on Twitter

💬6🔄10❤️66👀14221📊17

⚡ Powered by xgo.ing

Brand new Max Agency with @FactoryAI CTO & Co-Founder @EnoReyes!

LangChain (@LangChain) — Thu, 16 Jul 2026 14:38:20 GMT

Brand new Max Agency with @FactoryAI CTO & Co-Founder @EnoReyes!

Harrison Chase@hwchase17

New Max Agency with @FactoryAI CTO & Co-Founder @EnoReyes.

This was a particularly fun one. Since we're both building harnesses, we nerded out pretty deep.

Awesome conversation on why the harness matters more than the model running underneath it, how Factory built Missions, + more.

⏯️ YouTube: youtube.com/watch?v=HbUznY…

🎧 Apple:podcasts.apple.com/us/podcast/the…Z

🎧 Spotifyopen.spotify.com/episode/5CkX1d…ag

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬2🔄6❤️25👀7101📊4

⚡ Powered by xgo.ing

🎧 Apple: https://t.co/BFlHg8NQGH 🎧 Spotify: https://t.co/adiJoxN2dj ⏯️ YouTube: https://t.co/ctK...

LangChain (@LangChain) — Thu, 16 Jul 2026 14:38:20 GMT

🎧 Apple:podcasts.apple.com/us/podcast/the…H

🎧 Spotifyopen.spotify.com/episode/5CkX1d…dj

⏯️ YouTubeyoutube.com/watch?v=HbUznY…Il

💬0🔄0❤️6👀1751📊1

⚡ Powered by xgo.ing

How @Box uses Deep Agents middleware for Box Agent: 1️⃣Citation generation: Streaming of the answer...

LangChain (@LangChain) — Thu, 16 Jul 2026 12:37:39 GMT

How @Box uses Deep Agents middleware for Box Agent:

1️⃣Citation generation: Streaming of the answer + citation generation happens in parallel to avoid user interruption

2️⃣Prompt caching: Injects caching on multi-turn conversations, reducing cost + latency

3️⃣Context management: Summarizes conversation history after exceeding 170k tokens, preventing context overflow

langchain.com/blog/building-…

💬7🔄5❤️43👀7432📊14