Knowledge catalogue
Model-Harness-Task fit is very real. The world's best agents carefully tailor the harness around the model to take advantage of each model's unique intelligence & capabilities 🧠 Today we released Harn
Most pharma agent pilots never make it to production. We’re partnering with @Axtria to close this gap. Built on LangSmith, Axtria’s pharma-native AgentOps framework will give life sciences enterprises
New in Deep Agents: Harness Profiles. https://www.langchain.com/blog/tuning-deep-agents-different-models ✅ Model-specific profiles to adjust prompts, tools, and middleware. 📦 Profiles for @OpenAI, @An
Open Models are really smart Open Models are often way cheaper Open Models are fast for the CTOs & CFOs in the back, no need to fight, Open Models mean you can both be happy :) - potentially cutting c
own your agent harness 🤝 own your intelligence 🤝 own your evals 🤝 open ecosystems this doesn’t mean start from scratch, build on an open base harness where you can edit/extend existing primitives like
So excited for this - in the past four months I've written all my code using Deep Agents with: - Opus 4.6 - GPT-5.4 - GLM-5 - Kimi 2.6 - Opus 4.7 - GPT-5.5 Currently using 5.5 as my driver with Opus s
That's a quick tour through building and deploying a simple agent with DeepAgents deploy Was just a markdown file, a json file, and toml file Easy to set up, but robust deployment by the end Try out d
This entry documents the initial setup process for a DeepAgents project, specifically demonstrating how to use the `deepagents init` command to create a new project and assign it a name (in this examp
This is so good @hwchase17 walks through the complete setup of a Deep Agents deployment step-by-step It’s a great example of getting started fast with Deep Agents from the CLI! DeepAgents Deploy is th
LangChain is actively hiring for an unspecified position or role (#11), as confirmed by Harrison Chase on their official X account. The company directs interested candidates to their careers page at l
when you take an agent to production, you almost certainly need guardrails! deepagents makes it easy to add guardrails via middleware. guardrails can be used for 1. control flow, like model/tool retri
At @ListenLabs, agents analyze data from conversations by building their own tables — adding columns like 'user sentiment,' filling in values automatically, then charting the results. Co-Founder & CTO
Both are great models and neither wins everywhere. I use both Opus and 5.5 depending on the task. LangSmith Fleet lets you choose the model for each agent, so you can match it to the work https://www.
first up in the 'going to production' series: durable execution! long running agents need to be able to 1. survive crashes 2. resume after an indefinite pause durable execution solves this by checkpoi
free agents from Harrison? I’m in 🫡 drop the agent of your dreams below and it’ll (prob) magically exist soon i want an agent that helps me riff on ideas for tweet-length visual essays and researches
Harrison Chase discussed deep agents and LangChain's SDK for building autonomous agents on the Talk Python podcast (episode 543). The conversation likely covered LangChain's tools, capabilities, and b
Harrison Chase expresses his passion for working with early-stage companies and startups focused on AI development, indicating his entrepreneurial mindset and enthusiasm for the AI innovation space. T
If you're going to be at @_odsc, head over to @sydneyrunkle's talk Deep Dive on Deep Agents. Today @ 11:05 AM ET speaking at odsc east today!! DM me if you're in boston and want to chat about deep age
Harrison Chase announced plans to create multiple deepagents examples using the deepagent deploy tool and solicited community input on which examples would be most valuable. This post likely seeks fee
.@jakebroekhuizen joined LangChain as one of our first deployed engineers. In just over two weeks, he’s adding MC to his resume as he takes the stage at our agent conference Interrupt. A quick convers
Open Models & a potential looming Haiku-apocalypse? 🚀 chart comparison UI courtesy of @OpenRouter there's a large class of problems where you don't need frontier intelligence. you want cheap, fast, an
Switched out Sonnet 4.6 for GLM 5.1 through @FireworksAI_HQ while doing some tests with @LangChain Fleet Agents Went from 0.19 per run with Sonnet to 0.07 with GLM 5.1 You can also drop Kimi K2.6 and
last week we dropped a super comprehensive guide on runtime requirements for long running agents! this week i'll be diving into each requirement and runtime capability that meets it, here's the lineup
🗓️ @mondaydotcom is scheduled for Interrupt. Monday Sidekick is an AI assistant that can execute work, manage tasks, and conduct research autonomously. At Interrupt, the Agent Conference by LangChain,
Progressive disclosure keeps agents focused. Join us at Interrupt May 13-14 for a conversation with @levie about @Box + Deep Agents https://interrupt.langchain.com/ AI agents work better when they bri
The EU AI Act is the first comprehensive regulation for AI systems, and it’s right around the corner. With the clock running down, we took a deeper look at what these requirements mean for your agents
The April 2026 LangChain newsletter from Harrison Chase covers the latest updates, developments, and announcements from the LangChain team regarding their language model framework and tools. The newsl
Thoth 𓁟 v3.17.0 is out 🚀 Designer Studio just got a serious upgrade + video generation + seamless in-app updates Build full app prototypes, storyboards, pitch decks, docs, landing pages - all in one p
Alpha Eval: Agents Making Evals as a Multi-Player Game This diagram and blurb is largely a research riff with Claude on building data generation systems to get closer to the holy grail of self-improvi
Harrison Chase, co-founder of LangChain, expressed enthusiasm about an upcoming LangChain Interrupt conference event scheduled for two weeks from his post date. He characterized it as the best AI deve
LangChain Community Spotlight: Distributed LangGraph Architecture with RemoteGraph 🔗 Production-ready example for distributed LangGraph apps with HTTP-invoked subgraphs. Key insight: RemoteGraph retur
the power of open source, open harnesses, open agents, and communities 🔥 super fun to be a part of a community of builders who share cool work like this in the open. also been fun to see builders shar
Twintivo developed a system using three asynchronous deep agents with LangChain to reduce operational downtime in manufacturing facilities. The approach leverages asynchronous processing to enable mul
A perfect example of how we use agents for internal tooling at LangChain: 𝚍𝚎𝚎𝚙𝚊𝚐𝚎𝚗𝚝𝚜 lets us keep our docs code fresh against a moving substrate great blog by @naomi_pen on how we're using deepagents
agents that are made to support specific teams end up helping a ton! great read on how we use deepagents every day to maintain our docs. Our docs are both a reference for our libraries but also a grea
Deep Agents middleware is a great invention. You get a really strong default harness and a clean way to customize every part of it DeepAgents - it’s all you need - batteries included if you want, but
DeepAgents is a framework or tool that provides comprehensive, ready-to-use components for building AI agents while maintaining flexibility for customization. The 'batteries included' approach suggest
DeepAgents Sandbox — a lightweight native Linux sandbox for deepagents It gives full isolation for safely running LLM/agent-generated code — no Docker, no VMs, no cloud dependency. Super fast and secu
everyones gonna be here! I’ll be in San Francisco from May 9-16 for @LangChain Interrupt 🦜 If you’re around, DM me, I’d love to chat about applied AI, agents, and running agentic systems in production
GPT-5.5 now available in Deep Agents! GPT-5.5 is now available in the API. The model brings higher intelligence and stronger token efficiency to complex work, helping tasks get done with fewer retries
LangChain's DeepAgents tool is being used to automatically test and maintain the accuracy of documentation code snippets, ensuring they remain current and functional. This approach addresses a common
LangChain's careers page lists job opportunities at the company, which develops tools and frameworks for building applications with large language models. The page likely includes open positions, comp
A user asks Harrison Chase about whether there are deepagents skills comparable to the claude-api skill that could help with building applications using deepagents framework. This appears to be a ques
I built deepagents-sandbox — a native Linux sandbox backend for Deep Agents. No Docker. No VM. Agents get a writable /workspace, blocked network by default, memory/PID limits, and timeout enforcement.
Harrison Chase announced his presence in San Francisco from May 9-16 to attend LangChain Interrupt, a LangChain-related event. He invited interested parties to contact him to discuss applied AI, agent
LangSmith for Startups Spotlight: @AdaptiveBuilds Adaptive is the AI-native project accounting platform built for construction. They embed AI agents directly into job costing, billing, and forecasting
There is lots of AI noise on Twitter but also lots of signal when you know where to find it. When @Vtrivedy10 is quoting @LakshyAAAgrawal - you have found the signal and you should slow down and dig i
Very cool demo by @Box how progressive skill loading works in practice 👀 The agent walks through onboarding step-by-step: load employee → load skill → scoped search → synthesize Instead of one giant p
yes! https://github.com/langchain-ai/langchain-skills/tree/main/config/skills @hwchase17 Is there any deepagents skill similar to the claude-api skill to help me build apps with deepagents better? htt
@benswerd there are tradeoffs but we've spoken to folks doing both inside and outside and the split is pretty much 50:50 in our experience. I've found @hwchase17's list of tradeoffs the most accurate
LangChain, an open-source framework for developing applications with large language models, is recruiting new team members as shared by co-founder Harrison Chase on X (Twitter). The careers page invit
come work with us 🚀 everyone here is rlly nice, smart, curious, ships like crazy, and we make great Slack stickers I work with some world class people @LangChain! We're hiring for all sorts of roles -
Harrison Chase, co-founder and CEO of LangChain, appeared in a startup spotlight interview with Stephanie Wong. The discussion likely covered LangChain's development, its applications in AI and langua
Evals ~= Environments…they’re one of the best investments a team can make for improving agents Step 0: Turn On Tracing for Agents Step 1: Point compute at Traces to understand agent behavior, segment
Great food, even better company! Last night, we teamed up with First Commits to co-host our first dinner together for founding engineers at Penny Roma. We shared honest conversations and real stories
I work with some world class people @LangChain! We're hiring for all sorts of roles - check them out here: https://www.langchain.com/careers The 15 most talent-dense Tech Companies from @paraformtalen
Just 2 weeks ago I've build https://github.com/christian-bromann/slidev-agent and now the Fleet team has shipped a much better version of that within Fleet 🤯 One of my favorite features we’ve shipped
New in LangSmith Fleet: Create and edit files with your agent. Your agent can now work with files directly. Create documents, presentations, and webpages inside a conversation, or upload your own file
New Max Agency! 🎙️ @hwchase17 🎙️ @ListenLabs Co-Founder/CTO @florian_jue 🎙️ Talked to @ListenLabs co-founder + CTO @florian_jue in the latest Max Agency. Really enjoyed hearing about the architectural
One of my favorite features we’ve shipped in Fleet recently is the presentation viewer. Fleet agents are very good at writing code, so we thought why not have a built in way for them to design slides,