Knowledge catalogue
New in LangSmith Evaluation: ✅ Evaluator template library ✅ Reusable evaluators Everything you need to know → https://www.langchain.com/blog/reusable-langsmith-evaluator-templates?utm_source=x&utm_med
there's a lot to be excited about with this release! * For one this solves a huge issue just generally with long-running agent UX * For two this is a key unlock for us to go test more adaptive methods
very excited for this one! a year ago, most of what was being traced to LangSmith was 'LLM apps'. now everything is becoming an agent. with that shift, it's getting harder to know what your software i
communication is hard! structured outputs make its more clear how subagents should communicate back to the main agent deepagents now supports structured output for subagents! an under appreciated piec
crons, part of langsmith deployments! https://docs.langchain.com/langsmith/cron-jobs I’m not sure whether LangChain supports this yet, but it might be worth considering scheduling and cron-style jobs
`deepagents deploy` now supports user scoped memory! add a user/ directory in your project so each user gets their own writable AGENTS.md, seeded on first deploy and persisted across conversations. yo
deepagents now supports structured output for subagents! an under appreciated piece of context engineering is figuring out what context is passed back from subagents to the main agent. now you can def
Have found the same things! Using glm-5 as a daily driver for a lot of things We've tested new OSS models the moment they're released for a while at Lindy. Inference is our #1 cost by a lot (more than
Harrison Chase, co-founder of LangChain, was tagged or mentioned in a post by user @colesmcintosh expressing enthusiasm or confidence about deep agents ('deepagents 4 sure'), likely referencing advanc
New in LangSmith Fleet: Tool access controls and usage tracking. 📊 Track cost and usage by user, agent, and tool from a single dashboard 💳 Set spend limits per user or team to prevent surprises ✅ Cont
Rippling AI was the most successful launch we've ever done. On the heels of this launch, Rippling's revenue is now growing 78% YoY (at ARR over $1 Billion). And this growth rate has now increased, eve
This is awesome and makes things much more composable. Love it deepagents now supports structured output for subagents! an under appreciated piece of context engineering is figuring out what context i
Track usage and costs across your users, agents and tools. We're also shipping better access controls for your tools & agents: - Set spend limits on agents - Set spend limits for users - Control what
User scoped memory is one of those things that doesn’t matter if you’re building a toy agent for yourself, but when you release at scale you gotta get it right Deepagents deploy helps you do that, eas
Harrison Chase, the creator of LangChain, shares reflections or opinions on directions for modern AI development, tooling, or the broader technology landscape. The post likely explores strategic or ph
Big release here! Async subagents will become more and more of a thing, as subagents get longer running and you don’t want to block the event loop 🚀 deepagents 0.5 release 👉 Async subagents - kick off
Building agents locally does not mean they’re ready to deploy in production LangSmith deployments helps with that 🔐 One deployment, isolated data per user. Add custom auth so every user gets their own
Content moderation is a great use case for moderation new middleware integration just dropped! the langchain azure ai package now ships w/ a suite of content moderation middleware! use this for text/i
🚀 deepagents 0.5 release 👉 Async subagents - kick off background tasks on any Agent Protocol backed server while you continue to interact with the main agent. Start multiple background tasks in parall
Harrison Chase's post explores the divergent strategic incentives around memory in AI agent systems, arguing that for those building agent frameworks, persistent memory creates compounding value and c
Harness Engineering Derived from what Models can’t do alone: It feels like a good time to step back and reshare some basic mental models for why harnesses exist in the first place - working backwards
here’s a good application of harness permissions Programmatically Enforced Auto-Research: - auto-research loops usually expose a set of files that the agent is allowed to edit to hill climb a metric/e
ICYMI -- last week we released `deepagents deploy`, the fastest way to take a highly capable, long running agent to production. agents are becoming more and more standardized, and we're betting on thi
Love seeing this open-sourced. Had a great chat with @nicoalbanese10 some weeks ago where he hinted to something like this. Great reference architecture for cloud coding agents. Open Agents gives you
new middleware integration just dropped! the langchain azure ai package now ships w/ a suite of content moderation middleware! use this for text/image moderation and prompt injection guards! https://d
🔐 One deployment, isolated data per user. Add custom auth so every user gets their own scoped threads, runs, and conversation history — with per-user data isolation and role-based access using any aut
Open Harness 🤝 Deployed Agents if you wanna use Claude, GLM5, and Codex in your deployed harness then you should be able to! deepagents deploy has easy configs to let users customize their harness and
☁️ Salesforce tools now in Fleet One of the most requested features we've gotten, and it's now a first-class supported tool in Fleet! Just sign in with your Salesforce account, and start using it imme
The LangChain OpenRouter package has broken into the top 20 applications on the OpenRouter platform, representing a 175% growth in usage within a single week. This milestone highlights the rapid adopt
this is a fundamental building block for `deepagents deploy` we're designing a memory layer built for multi-tenant systems, so memory can be scoped to a user, agent, or organization please dm me if th
Thoth v3.14.0: multi-provider cloud and multi-provider image generation. Five cloud providers now work as first-class citizens: OpenAI, Anthropic, Google, xAI, and OpenRouter. Image generation spans t
Two major shifts will be seen in Agentic AI after Harness and YOU MUST KNOW. 1. Workflow design of your agents matters a lot more than any frontier model selection. Till now we have mostly focused on
We've tested new OSS models the moment they're released for a while at Lindy. Inference is our #1 cost by a lot (more than payroll) — cutting it by 2-5x would be transformative. Last year, OSS models
and if this sounds like fun (it is), we're hiring! https://www.langchain.com/careers Fun fact - we have no one with dev rel as a title (and never had) Everyone has always been just an engineer buildin
deepagents subagents are just tools. when you call a subagent, thats conceptually a function call. this is the simplest mental model for building multiagent systems. https://docs.langchain.com/oss/pyt
Fun fact - we have no one with dev rel as a title (and never had) Everyone has always been just an engineer building things and then talking about why those things matter and are cool @LangChain liter
Harrison Chase, co-founder of LangChain, expressed strong conviction on X (formerly Twitter) that LangChain has the best team in the AI framework space, emphasizing the consistent quality and volume o
just did our Monday morning weekly dev rel plan, feel free to steal :) shoutout to the great community that engages with us and gives us tons of feedback which makes doing this loop fun every week ❤️
Harrison Chase, co-founder of LangChain, shared or engaged with a post on X (formerly Twitter) praising LangChain's developer relations team for producing high-quality technical and educational conten
langgraph persistence lets you checkpoint agent state at every step so you can pause, resume, and replay from any point. essential for long-running agents. docs: https://docs.langchain.com/oss/python/
Harrison Chase, co-founder and CEO of LangChain, expressed gratitude for his team in a post on X (formerly Twitter). The post likely highlights appreciation for colleagues and collaborators contributi
Memory operations, including retrieval, prioritization, compaction awareness, should be native and baked into the harness. 𝐖𝐢𝐭𝐡𝐨𝐮𝐭 𝐭𝐡𝐞 𝐩𝐫𝐨𝐩𝐞𝐫 𝐢𝐧𝐭𝐞𝐫𝐚𝐜𝐭𝐢𝐨𝐧 𝐛𝐞𝐭𝐰𝐞𝐞𝐧 𝐡𝐚𝐫𝐧𝐞𝐬𝐬 𝐚𝐧𝐝 𝐦𝐞𝐦𝐨𝐫𝐲, 𝐦𝐞𝐦𝐨𝐫𝐲 𝐚𝐥𝐨𝐧𝐞 𝐢𝐬 𝐩𝐨
🔒 new in deepagents: filesystem permissions shared resources and org-wide policies are exactly the kind of files you want your agent to read but never overwrite. filesystem permissions let you enforce
The model is not the agent. The harness is. You need to read this recent study, and a blog post from @hwchase17 ... (links below). It will resonate deeply. This diagram from a recent paper captures so
LangChain has launched a new podcast focused on the theme of empowerment, as announced by Harrison Chase on X (formerly Twitter). The podcast likely features discussions around AI development, buildin
Harrison Chase discusses the tradeoff between speed and focus when building a core product using a frontier model versus developing more customized solutions. Using a frontier model with a standard ha
Harrison Chase, co-founder of LangChain, shared a post emphasizing the critical importance of the 'harness' in AI agent systems, arguing that the harness essentially functions as the agent's memory an
This post completely misses the point of @sarahwooders 's original article. The whole point is that memory == context engineering, so it can't be a 'thin conductor'. Saying 'memory is just markdown' t
when you take agents to production, you need to think about guardrails we provide 2 abstractions for guardrails 1. middleware provides hooks around the agent loop that you can use to handle retries, e
Harrison Chase, co-founder of LangChain, endorsed the perspective that memory in AI agents is fundamentally a form of context, emphasizing that effective context management is the core requirement for
“Above the api line” Good phrase GBrain is my attempt to be in control of my own personal AI that could become my intentionally designed cognitive armor Open source open prompts means you aren’t under
Agent harnesses dominate agent building and tie intimately to memory. Closed harnesses behind proprietary APIs force yielding control of agent memory to third parties. Memory enables sticky, personali
Harrison Chase, co-founder of LangChain, shared or engaged with commentary emphasizing the importance of owning your own memory harness in AI applications rather than relying on third-party API-based
Deepagents is an open-source project by LangChain that implements deep research-style agentic workflows, enabling AI agents to perform iterative, multi-step research and reasoning tasks. The repositor
deepagents is a harness / planning tool, filesystem backend, subagent spawning, memory management / thats the stack that matters / models are the cpu, the harness is the os / anyways, check it out htt
Directionally correct Open memory standards will need to emerge But it’s so early right now. We’re still just figuring out what best practices are. And so a lot is at the mercy of harnesses Agents.md
Each workflow in Thoth is a full LangGraph agent which can call subagents which themselves are LangGraph agents. Just describe what you want in plain English and it builds a full multi-step pipeline.
'every memory system is choosing a position on the raw/derived spectrum. and neither extreme works.' the axis nobody talks about: ownership > memory is your agent's compounding advantage > derived fac
feels right. once implementation gets cheap, the leverage moves into review and guardrails. e.g. specs, constraints, tests, hooks. otherwise it's mostly just generating more work for humans to fix up
Harrison Chase, co-founder of LangChain, has been advocating that individuals should prioritize owning their personal 'memory and skills folder' as the most critical store of value in the current AI l