Top all-time · #1085
LangChain Blog
Company blog · blog.langchain.devaiprogramming
LangChain Blog is the company blog at blog.langchain.dev, writing about ai and programming. Since 2023, 64 different Hacker News readers have linked it 77 times, most often “LangChain Announces 10M Seed Round”. It is still writing: the last post was on 2026-10-30, and you can follow it by feed.
Too few sampled comments (19) to say how often HN recommends it.?
Why HN links it
HN readers link LangChain's blog for posts on what an AI agent is, RAG evaluation, LLM and SQL, memory and vector databases. Many comments about it discuss the company instead.
Summarised by Claude from a sample of 19 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Explore tutorials, case studies, and technical insights on building AI agents with LangSmith, Deep Agents, LangGraph, and LangChain. Learn from experts.
Most-linked posts?
- LangChain Announces 10M Seed Round5 people · 5 mentions · first linked 2023-04-04
- How to think about agent frameworks4 people · 4 mentions · first linked 2025-04-20
- LLMs and SQL3 people · 3 mentions · first linked 2023-03-21
- What Is an Agent?3 people · 3 mentions · first linked 2024-06-30
- LangChain's State of AI 2023 [Report/Article]3 people · 3 mentions · first linked 2023-12-22
- LangChain and Chroma2 people · 2 mentions · first linked 2023-02-13
- Autonomous Agents and Agent Simulations2 people · 2 mentions · first linked 2023-04-19
- Winning in AI means mastering the new stack2 people · 2 mentions · first linked 2024-02-16
- /evaluating-rag-pipelines-with-ragas-langsmith/2 people · 2 mentions · first linked 2023-09-20
- Plan-and-Execute Agents2 people · 2 mentions · first linked 2023-05-10
What Hacker News says?
Good thing they didn't raise money to develop this piece of crap. https://blog.langchain.dev/announcing-our-10m-seed-round-led...
Comment linking /announcing-our-10m-seed-round-led-by-benchmark/
on “Why we no longer use LangChain for building our AI agents”Submitted Langchain $25M Series A, Langsmith GA as a story · 22 points
HN discussioninteresting to contrast the recent memory releases - https://mastra.ai/docs/agents/01-agent-memory - https://blog.langchain.dev/langmem-sdk-launch/ - https://help.getzep.com/concepts#adding-memory not sure where all this is leading yet but glad people are exploring.
Comment linking /langmem-sdk-launch/
on “Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby”Submitted LangChain Announces 10M Seed Round as a story · 18 points
HN discussionWe are building this with https://lets.dev . We believe there will be great demand for less capable, but much more determinisic agents. I also recommend everyone to read "What is an agent?" by Harrison Chase. https://blog.langchain.dev/what-is-an-agent/
Comment linking /what-is-an-agent/
on “AI agents: Less capability, more reliability, please”Submitted Timescale Vector (PostgreSQL) now available in LangChain as a story · 13 points
HN discussionThis article talks about it somewhat I think as well. Highlighting the difference between more advanced workflows and agentic style systems vs 'agents' https://blog.langchain.dev/how-to-think-about-agent-framewor...
Comment linking /how-to-think-about-agent-frameworks/
on “Show HN: Rowboat – Open-source IDE for multi-agent systems”Submitted LangGraph and Composio Achieved 48.6% on SWE Bench as a story · 9 points
HN discussionIn the ~2 year timeframe we'll be using RAG. Longer term it gets more interesting. Assuming we can solve long (approaching infinite) context, and solve the issues with reasoning over long context that LangChan correctly identified[1] then it becomes a cost and performance (speed) issue. It is currently very very expensive to run a full scan of all knowledge for every inference call. And there are good reasons why da…
Comment linking /multi-needle-in-a-haystack/
on “Ask HN: Is RAG the Future of LLMs?”Submitted How to think about agent frameworks as a story · 7 points
HN discussionLangSmith integrates with OpenTelemetry: https://blog.langchain.dev/opentelemetry-langsmith/
Comment linking /opentelemetry-langsmith/
on “RAG Logger: An Open-Source Alternative to LangSmith”Submitted MCP – Flash in the Pan or Future Standard? as a story · 6 points
HN discussionRemember than LangChain raised $10m a few months ago https://blog.langchain.dev/announcing-our-10m-seed-round-led... (wait, over a year ago!)
Comment linking /announcing-our-10m-seed-round-led-by-benchmark/
on “LangChain Is a Black Box”Submitted Announcing LangChain v0.1.0 as a story · 5 points
HN discussionAmong software engineers "LLM with access to tools" shows up a lot. Or sometimes "LLM in a loop" or "LLM on a schedule / that can respond to triggers". Or even just an LLM with a custom system prompt. Thermostat is common: an AI system that can react to its environment and continually make changes based on that ongoing feedback. The ability to act on a loop in order to reach a predefined goal. I think of ChatGPT Cod…
Comment linking /what-is-an-agent/
on “MIT researchers develop an efficient way to train more reliable AI agents”Submitted GPTeam: A Multi Agent Simulation as a story · 5 points
HN discussionI just finished augmenting some of the Spider and WikiSQL data on huggingface [1] I initially intended to train a text-to-sql LLM that would take a natural language question and be provided the CREATE TABLE statements to provide some grounding for the response. So instead of hallucinating the column and table names by using the question alone, I was hoping the CREATE TABLE statement would limit the choices. We'll se…
Comment linking /llms-and-sql/
on “Finetuning Large Language Models”Submitted LangChain's Second Birthday as a story · 4 points
HN discussionLangchain wrote about LLMs and SQL, and although it's about SQL, it's still a great read, especially the references. https://blog.langchain.dev/llms-and-sql/ I'm also super keen for the 32k API limit for OpenAI, that's going to be great.
Comment linking /llms-and-sql/
on “Finetuning Large Language Models”Submitted What Is an Agent? as a story · 4 points
HN discussionThey're well-funded; go ahead and criticize them. https://blog.langchain.dev/announcing-our-10m-seed-round-led...
Comment linking /announcing-our-10m-seed-round-led-by-benchmark/
on “The Problem with LangChain”Submitted BCGX Releases AgentKit, a Full-Stack Starter Kit for Building Constrained Agents as a story · 4 points
HN discussionLangchain previously had a nice blogpost about how they build their RAG chatbot, maybe there are some helpful hints in there: https://blog.langchain.dev/building-chat-langchain-2/
Comment linking /building-chat-langchain-2/
on “Choosing vector database: a side-by-side comparison”Submitted Launching LangGraph Templates as a story · 3 points
HN discussionYou might like this - https://www.youtube.com/watch?v=fWC4VxolWAk Blog on the same topic - https://blog.langchain.dev/evaluating-rag-pipelines-with-rag...
Comment linking /evaluating-rag-pipelines-with-ragas-langsmith/
on “Choosing vector database: a side-by-side comparison”Submitted Reflection Agents as a story · 3 points
HN discussionThanks for the advice! Some benchmarks here: https://blog.langchain.dev/zep-x-langchain-slow-chatbots/
Comment linking /zep-x-langchain-slow-chatbots/
on “Zep: Fast, scalable building blocks for production LLM apps”Submitted Mental Health Therapy as an LLM State Machine as a story · 3 points
HN discussionZep author here. LangChain is a great framework and has a very broad and active ecosystem. Many of LangChain's core components, such as chat history "memory," history summarization, entity extraction, vector search, and more, don't scale well in production. They operate in memory and often synchronously within the chat loop, resulting in poor user experiences and limiting deployment options. You can use third-party…
Comment linking /zep-x-langchain-slow-chatbots/
on “Zep: Fast, scalable building blocks for production LLM apps”Submitted LangChain's State of AI 2023 [Report/Article] as a story · 3 points
HN discussion
