# LangChain

LangChain is an open-source framework for building agents and LLM-powered applications.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## AI agent startup LangChain hits $3B valuation

DevFeed: [AI agent startup LangChain hits $3B valuation](<https://devfeed.tech/articles/ai-agent-startup-langchain-hits-3b-valuation-133239.md>)

Original publisher: [Read original article](<https://techcrunch.com/2026/11/13/ai-agent-startup-langchain-hits-3b-valuation/>)

Author: Julie Bort

Published: 2026-11-13T19:37:57Z

Content type: news

Language: en

Sources: [TechCrunch | AI News & Artificial Intelligence](<https://devfeed.tech/sources/techcrunch-ai-news-artificial-intelligence.md>)

Topics: [LangChain](<https://devfeed.tech/topics/langchain.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-management](<https://devfeed.tech/tags/agent-management.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [customers](<https://devfeed.tech/tags/customers.md>), [fundraising](<https://devfeed.tech/tags/fundraising.md>), [in-brief](<https://devfeed.tech/tags/in-brief.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [model](<https://devfeed.tech/tags/model.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [series-c](<https://devfeed.tech/tags/series-c.md>), [startup](<https://devfeed.tech/tags/startup.md>), [startups](<https://devfeed.tech/tags/startups.md>), [valuation](<https://devfeed.tech/tags/valuation.md>)

### AI overview

LangChain raised $300 million in a Series C at a $3 billion valuation, more than double its $1.25 billion valuation about a year earlier. After starting as an open source project for tasks such as web search and API calls, it shifted toward managing AI agents. Its LangSmith platform is presented as model-, cloud-, and ecosystem-agnostic, with a focus on containing agent behavior and ease of use. LangChain says it has 7,000 customers, including Harvey, Rippling, Clay, Nvidia, Toyota, and Salesforce. The article notes that other startups pitch similar advantages in a competitive market.

### Source excerpt

LangChain now claims 7,000 customers of its model and platform agnostic agent management tool LangSmith.

## LangChain Raises $300M Series C at $3B Valuation

DevFeed: [LangChain Raises $300M Series C at $3B Valuation](<https://devfeed.tech/articles/langchain-raises-300m-series-c-at-3b-valuation-133502.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/series-c>)

Author: LangChain Accounts

Published: 2026-11-13T16:06:29Z

Content type: news

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [observability](<https://devfeed.tech/topics/observability.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [control-plane](<https://devfeed.tech/topics/control-plane.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [company](<https://devfeed.tech/tags/company.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [platform](<https://devfeed.tech/tags/platform.md>), [raises](<https://devfeed.tech/tags/raises.md>), [series-c](<https://devfeed.tech/tags/series-c.md>), [valuation](<https://devfeed.tech/tags/valuation.md>)

### AI overview

LangChain says it raised $300 million at a $3 billion valuation in a round led by existing investor CapitalG, with participation from GIC, DFJ Growth, IVP and Sapphire Ventures. It presents LangSmith as a framework-agnostic platform for running, improving and governing agents, organized around runtime, improvement and governance. Described tools cover deployment and execution across cloud or customer environments, observability and evaluation, automated fixes and regression monitoring, trace-based fine-tuning, and centralized controls for model budgets, fallbacks, sensitive data and tool access. The announcement says more than 7,000 organizations use LangSmith and cites customer examples, including Workday reducing agent deployment time from five months to under a day; these are company-reported claims.

### Source excerpt

LangChain raises $300M Series C at a $3B valuation, led by CapitalG, to help every company own its intelligence with LangSmith, the agent engineering platform.

## AI agent tooling provider LangChain secures $300M investment

DevFeed: [AI agent tooling provider LangChain secures $300M investment](<https://devfeed.tech/articles/ai-agent-tooling-provider-langchain-secures-300m-investment-131046.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/12/ai-agent-tooling-provider-langchain-secures-300m-investment/>)

Author: Maria Deutscher

Published: 2026-11-12T23:24:06Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [LangChain](<https://devfeed.tech/topics/langchain.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [developer-tooling](<https://devfeed.tech/tags/developer-tooling.md>), [funding-round](<https://devfeed.tech/tags/funding-round.md>), [investment](<https://devfeed.tech/tags/investment.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [langgraph](<https://devfeed.tech/tags/langgraph.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [news](<https://devfeed.tech/tags/news.md>), [startup](<https://devfeed.tech/tags/startup.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [tooling](<https://devfeed.tech/tags/tooling.md>)

### AI overview

LangChain raised $300 million in a round led by Alphabet's CapitalG, with IVP, Sapphire Ventures, GIC and DFJ Growth participating; the article reports a $3 billion valuation. Its open-source tools cover different stages of agent building: LangChain connects agents to language models and tools, LangGraph coordinates multiple agents and can require human approval for sensitive actions, and Deep Agents adds planning, virtual file storage and subagent generation. LangSmith is the company's paid suite for managing agents in production, including version history and rollback, output comparisons, and observability that traces workflows, prioritizes technical issues and generates code fixes. The article also reports about 90 million monthly downloads of its open-source tools after last year's funding round, use of LangSmith by Autodesk and Cisco, and plans to grow to 850 employees by the end of 2027.

### Source excerpt

LangChain Inc., a startup with a set of popular open-source tools for building artificial intelligence agents, has raised $300 million in funding. The Wall Street Journal reported today that Alphabet Inc.'s CapitalG fund led the round. It was joined by IVP, Sapphire Ventures, GIC and DFJ Growth. LangChain is now worth $3 billion. San Francisco-based [...] The post AI agent tooling provider LangChain secures $300M investment appeared first on SiliconANGLE.

## UAEF: A framework-agnostic system for closed-loop evaluation of AI agents

DevFeed: [UAEF: A framework-agnostic system for closed-loop evaluation of AI agents](<https://devfeed.tech/articles/uaef-a-framework-agnostic-system-for-closed-loop-evaluation-of-ai-agents-129292.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/uaef-a-framework-agnostic-system-for-closed-loop-evaluation-of-ai-agents/>)

Author: Samaneh Aminikhanghahi

Published: 2026-11-11T15:50:55Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Trustworthy AI](<https://devfeed.tech/topics/trustworthy-ai.md>), [adapter pattern](<https://devfeed.tech/topics/adapter-pattern.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-evaluation](<https://devfeed.tech/tags/agent-evaluation.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [built-in](<https://devfeed.tech/tags/built-in.md>), [can](<https://devfeed.tech/tags/can.md>), [canonical](<https://devfeed.tech/tags/canonical.md>), [compare](<https://devfeed.tech/tags/compare.md>), [dimensions](<https://devfeed.tech/tags/dimensions.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [format](<https://devfeed.tech/tags/format.md>), [framework](<https://devfeed.tech/tags/framework.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [one](<https://devfeed.tech/tags/one.md>), [regressions](<https://devfeed.tech/tags/regressions.md>), [results](<https://devfeed.tech/tags/results.md>), [system](<https://devfeed.tech/tags/system.md>), [teams](<https://devfeed.tech/tags/teams.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [traces](<https://devfeed.tech/tags/traces.md>)

### AI overview

UAEF normalizes agent traces from supported frameworks and runtimes into a common AgentTrace, then applies the same selected metrics and comparison process across them. Its 36 built-in metrics cover seven dimensions; deterministic metrics score directly from traces and references, while LLM judge metrics use Amazon Bedrock. Ground-truth answers are optional, but tool-call evaluation requires expected tools, order, and arguments; metrics needing references are skipped when those are absent. Persisted experiments store metadata in DynamoDB and full results in S3, enabling per-metric comparisons, regression detection, and reports. PII screening occurs before storage, and stored-copy redaction is available. The Python library and web service share the evaluation engine and stores. Judge scores are evaluation signals rather than security controls, and comparisons require persisted runs.

### Source excerpt

The Universal Agent Evaluation Framework (UAEF) is a framework-agnostic system for evaluating AI agents. UAEF converts each framework's traces into one canonical format, scores them with 36 built-in metrics across 7 dimensions, and stores results so teams can compare agent versions and catch regressions.

## An LLM-Orchestrated Multi-Modal Chatbot for Tomato Disease Consultant

DevFeed: [An LLM-Orchestrated Multi-Modal Chatbot for Tomato Disease Consultant](<https://devfeed.tech/articles/an-llm-orchestrated-multi-modal-chatbot-for-tomato-disease-consultant-125977.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.10608>)

Author: Ngoc-Son Le, Khanh-Nghi Phan, Ngoc Hong Tran

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Chat Bot](<https://devfeed.tech/topics/chatbot.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>)

Tags: [chatbot](<https://devfeed.tech/tags/chatbot.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-et](<https://devfeed.tech/tags/cs-et.md>), [disease](<https://devfeed.tech/tags/disease.md>), [image](<https://devfeed.tech/tags/image.md>), [interface](<https://devfeed.tech/tags/interface.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [llama](<https://devfeed.tech/tags/llama.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mistral](<https://devfeed.tech/tags/mistral.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [offline](<https://devfeed.tech/tags/offline.md>), [plants](<https://devfeed.tech/tags/plants.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [remote](<https://devfeed.tech/tags/remote.md>), [streamlit](<https://devfeed.tech/tags/streamlit.md>)

### AI overview

The paper presents a chatbot that uses text symptom descriptions to suggest likely tomato diseases, basic treatments, and related image-based reasoning. It uses pretrained Mistral and Llama 3.2 models, with LangChain and Streamlit for a lightweight, offline-friendly interface aimed at growers without nearby technical expertise. The abstract describes experimental results as promising but says further improvement is needed before real-world deployment.

### Source excerpt

arXiv:2611.10608v1 Announce Type: new Abstract: This paper introduces a chatbot developed to assist in diagnosing common diseases in tomato plants through natural language interaction. Users can describe symptoms in text. Then, the chatbot responds with the most likely disease, and basic treatment suggestions and related image-based reasoning. The system leverages pre-trained Mistral and Llama 3.2 large language models. The system is also built using LangChain and Streamlit to provide a lightweight and offline-friendly interface. This work targets to support tomato growers a fast and accessible tomato plant health guidance when the technical expertise is not available nearby, especially in the remote areas. The experimental results are promising and encourage further improvement of the chatbot for future real-world deployment.

## How Stripe Built Kai on Deep Agents in 1 Week

DevFeed: [How Stripe Built Kai on Deep Agents in 1 Week](<https://devfeed.tech/articles/how-stripe-built-kai-on-deep-agents-in-1-week-124910.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/how-stripe-built-their-knowledge-ai-platform-on-deep-agents>)

Author: LangChain Accounts

Published: 2026-11-09T22:07:04Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [LangChain](<https://devfeed.tech/topics/langchain.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [accelerate](<https://devfeed.tech/tags/accelerate.md>), [accelerated](<https://devfeed.tech/tags/accelerated.md>), [adopting](<https://devfeed.tech/tags/adopting.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agent-infrastructure](<https://devfeed.tech/tags/agent-infrastructure.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [company](<https://devfeed.tech/tags/company.md>), [deep](<https://devfeed.tech/tags/deep.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [langgraph](<https://devfeed.tech/tags/langgraph.md>), [stripe](<https://devfeed.tech/tags/stripe.md>), [users](<https://devfeed.tech/tags/users.md>), [wide](<https://devfeed.tech/tags/wide.md>)

### AI overview

Stripe built Kai, a company-wide assistant for non-engineers, with one engineer in one week using Deep Agents as its agent foundation. Deep Agents supplies the tool-calling loop, middleware, streaming, and state management; Stripe adds its security and internal services, configurable agent setups, and UI. Kai connects to internal data, Slack, and Google Suite, and produces artifacts alongside session chats. A virtual filesystem backed by S3 persists files across turns through sandbox sync-in and sync-out; a separate sandbox runs analytics code and processes files, while summarization manages long sessions and context costs. Skills owned by teams load tools dynamically, but selection is becoming difficult across 500+ MCP tools and 1,000+ skills; the excerpt reports quality degradation beyond 150 skills with the system prompt and describes hybrid prefiltering as planned work. After open preview, users grew from 296 to over 5,000 in roughly four weeks; the excerpt also reports 83% weekly use. Governance, behavioral personalization, and collaboration across sessions remain areas of work.

### Source excerpt

Learn how Stripe built Kai, a company-wide AI agent on LangChain, LangGraph, and Deep Agents, reaching 5,000 users in roughly 4 weeks.

## Agent Framework vs. Agent Harness, clearly explained!

DevFeed: [Agent Framework vs. Agent Harness, clearly explained!](<https://devfeed.tech/articles/agent-framework-vs-agent-harness-clearly-explained-117804.md>)

Original publisher: [Read original article](<https://blog.dailydoseofds.com/p/agent-framework-vs-agent-harness>)

Author: Avi Chawla

Published: 2026-11-03T21:36:04Z

Content type: article

Language: en

Sources: [Daily Dose of Data Science](<https://devfeed.tech/sources/daily-dose-of-data-science.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Model Routing](<https://devfeed.tech/topics/model-routing.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>)

Tags: [abstractions](<https://devfeed.tech/tags/abstractions.md>), [actions](<https://devfeed.tech/tags/actions.md>), [affinity](<https://devfeed.tech/tags/affinity.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-framework](<https://devfeed.tech/tags/agent-framework.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agent-orchestration](<https://devfeed.tech/tags/agent-orchestration.md>), [agent-tools](<https://devfeed.tech/tags/agent-tools.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [attention](<https://devfeed.tech/tags/attention.md>), [faster](<https://devfeed.tech/tags/faster.md>), [framework](<https://devfeed.tech/tags/framework.md>), [harness](<https://devfeed.tech/tags/harness.md>), [has](<https://devfeed.tech/tags/has.md>), [vs](<https://devfeed.tech/tags/vs.md>)

### AI overview

Frameworks provide components for models, tools, state, and orchestration; harnesses package an agent loop with an execution environment and operating conventions such as file access, context management, progress tracking, and delegation. The choice depends on what must be controlled: explicit workflows suit known sequences and approval rules, while a configurable harness can reduce work when an agent's next action depends on evidence it gathers during a task. Many systems combine both, using a workflow for authorization and outcome checks and a harness for investigation. For long-running tasks, keep progress inspectable through separate artifacts such as commits, test results, and task files. Evaluate recovery after tool failures, restart behavior, completion checks, and approval limits, including for delegated agents. The text names LangGraph as supporting deterministic and model-driven steps, and Deep Agents as adding filesystem tools, context offloading, and subagent support on top of LangChain and LangGraph.

### Source excerpt

+ a technique for 23x faster attention!

## How to Build Durable Chat Memory for RAG Using ScyllaDB and LangChain

DevFeed: [How to Build Durable Chat Memory for RAG Using ScyllaDB and LangChain](<https://devfeed.tech/articles/how-to-build-durable-chat-memory-for-rag-using-scylladb-and-langchain-112510.md>)

Original publisher: [Read original article](<https://hackernoon.com/how-to-build-durable-chat-memory-for-rag-using-scylladb-and-langchain?source=rss>)

Author: ScyllaDB

Published: 2026-11-02T14:15:18Z

Content type: tutorial

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [AI chatbot continuity](<https://devfeed.tech/topics/ai-chatbot-continuity.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [scylladb](<https://devfeed.tech/topics/scylladb.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Cohere API for embeddings](<https://devfeed.tech/topics/cohere-api-for-embeddings.md>)

Tags: [2026-2](<https://devfeed.tech/tags/2026-2.md>), [abstraction](<https://devfeed.tech/tags/abstraction.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-applications](<https://devfeed.tech/tags/ai-applications.md>), [all](<https://devfeed.tech/tags/all.md>), [build](<https://devfeed.tech/tags/build.md>), [chat](<https://devfeed.tech/tags/chat.md>), [context](<https://devfeed.tech/tags/context.md>), [conversational-ai-persistence](<https://devfeed.tech/tags/conversational-ai-persistence.md>), [good-company](<https://devfeed.tech/tags/good-company.md>), [history](<https://devfeed.tech/tags/history.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [langchain-persistent-memory](<https://devfeed.tech/tags/langchain-persistent-memory.md>), [langchain-scylladb-integration](<https://devfeed.tech/tags/langchain-scylladb-integration.md>), [memory](<https://devfeed.tech/tags/memory.md>), [rag](<https://devfeed.tech/tags/rag.md>), [rag-chatbot-memory](<https://devfeed.tech/tags/rag-chatbot-memory.md>), [scalable-rag-architecture](<https://devfeed.tech/tags/scalable-rag-architecture.md>), [scylladb](<https://devfeed.tech/tags/scylladb.md>), [scylladb-vector-database](<https://devfeed.tech/tags/scylladb-vector-database.md>), [scylladb-vector-search](<https://devfeed.tech/tags/scylladb-vector-search.md>), [search](<https://devfeed.tech/tags/search.md>), [using](<https://devfeed.tech/tags/using.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The example combines ScyllaDB vector search with LangChain so a RAG chatbot can retrieve documents and retain conversation history across restarts and replicas. It connects through the Cassandra-compatible driver and `cassio.init()`, embeds document chunks with local `all-MiniLM-L6-v2` embeddings, and uses LangChain's Cassandra vector store with an HNSW index. `CassandraChatMessageHistory` stores messages by `session_id`; `RunnableWithMessageHistory` loads prior turns and appends new ones, so replicas using the same ID can resume a conversation. The excerpt says embeddings can be switched to other LangChain-supported providers and identifies ScyllaDB 2026.2 as enabling this integration. The stated example is a setup walkthrough, not comparative performance evidence.

### Source excerpt

Learn how to use ScyllaDB Vector Search and persistent chat history with LangChain to build RAG chatbots that retain context across restarts and replicas.

## Build Generative UI Apps with A2UI & CopilotKit Agents

DevFeed: [Build Generative UI Apps with A2UI & CopilotKit Agents](<https://devfeed.tech/articles/build-generative-ui-apps-with-a2ui-copilotkit-agents-107151.md>)

Original publisher: [Read original article](<https://developers.googleblog.com/build-generative-ui-apps-with-a2ui-copilotkit-agents/>)

Author: Google A2UI Team; Atai Barkai

Published: 2026-10-30T04:35:29.705865Z

Content type: article

Language: en

Sources: [Google Developers Blog](<https://devfeed.tech/sources/google-developers-blog.md>)

Topics: [a2ui](<https://devfeed.tech/topics/a2ui.md>), [google-adk](<https://devfeed.tech/topics/google-adk.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>)

Tags: [a2ui](<https://devfeed.tech/tags/a2ui.md>), [adk](<https://devfeed.tech/tags/adk.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [apps](<https://devfeed.tech/tags/apps.md>), [aws](<https://devfeed.tech/tags/aws.md>), [build](<https://devfeed.tech/tags/build.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-ui](<https://devfeed.tech/tags/generative-ui.md>), [google](<https://devfeed.tech/tags/google.md>), [google-adk](<https://devfeed.tech/tags/google-adk.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [learn](<https://devfeed.tech/tags/learn.md>), [learn-how-to](<https://devfeed.tech/tags/learn-how-to.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [render](<https://devfeed.tech/tags/render.md>), [sdks](<https://devfeed.tech/tags/sdks.md>), [ui](<https://devfeed.tech/tags/ui.md>), [using](<https://devfeed.tech/tags/using.md>)

### AI overview

A2UI lets agents compose interfaces from a frontend's declared component catalog, using a framework-agnostic format that AG-UI can stream to the client. CopilotKit's documented setup connects an AG-UI-compatible agent to its runtime, defines component descriptions and Zod prop schemas, maps those definitions to frontend renderers, and passes the catalog to the provider. The Basic Catalog offers 18 general-purpose primitives; the text says production apps commonly define custom catalogs. A2UI also supports more controlled or open-ended generation, with tradeoffs: predefined components constrain customization, while generated code can drift from the design system and runs in a sandboxed iframe. For interactive flows, inputs bind to data paths and buttons send selected values back over the same stream; client-side validation can show errors without a model call. The article gives Google ADK as a setup example and says other AG-UI-compatible frameworks use the same pattern.

### Source excerpt

See Google A2Ui in action! Learn how to natively render agentic UIs across Langchain, AWS Strands, Microsoft agents, and Google ADK using CopilotKit SDKs for A2UI.

## How to build evidence-grounded agent memory with OpenWiki and Graphs

DevFeed: [How to build evidence-grounded agent memory with OpenWiki and Graphs](<https://devfeed.tech/articles/how-to-build-evidence-grounded-agent-memory-with-openwiki-and-graphs-105682.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/building-agent-memory-openwiki-graphs>)

Author: LangChain Accounts

Published: 2026-10-28T17:28:42Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [agents](<https://devfeed.tech/tags/agents.md>), [build](<https://devfeed.tech/tags/build.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [graph](<https://devfeed.tech/tags/graph.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [layer](<https://devfeed.tech/tags/layer.md>), [memory](<https://devfeed.tech/tags/memory.md>), [open](<https://devfeed.tech/tags/open.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [persistent-memory](<https://devfeed.tech/tags/persistent-memory.md>), [reuse](<https://devfeed.tech/tags/reuse.md>), [source](<https://devfeed.tech/tags/source.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [used](<https://devfeed.tech/tags/used.md>), [wiki](<https://devfeed.tech/tags/wiki.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

In a synthetic insurance library of 111 long-form documents, an OpenWiki compiled from source material made an agent answering connected, cross-document questions about five times as accurate as keyword search alone (0.52 vs. 0.10) and reduced cost per correct answer from about $0.55 to $0.19. For simple lookups, accuracy was similar and search was faster. OpenWiki synthesizes sources into linked, cited pages; claims link to source lines and hashes help flag changes for review. A lightweight evidence graph makes citations and document relationships explicit: claims cite paragraph-level passages, while typed edges capture references and supersession. The graph took under a second to build without additional model calls, and gave the agent `locate` and `expand` tools to follow evidence paths. Compared with the wiki alone, it increased accuracy 27%, doubled citation consistency, reduced median answer time 40%, and cut cost per correct answer 58%. These retrieval costs exclude wiki compilation and updates; the results come from a synthetic benchmark, and graph-derived edges still depend on the accuracy of model-generated wiki citations.

### Source excerpt

LangChain used OpenWiki, its open-source wiki compiler, and an evidence graph to build a persistent memory layer that preserves knowledge for agents to reuse across tasks. Learn how.

## The five components of building a "company harness"

DevFeed: [The five components of building a "company harness"](<https://devfeed.tech/articles/the-five-components-of-building-a-company-harness-100224.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/components-building-company-harness>)

Author: LangChain Accounts

Published: 2026-10-25T18:06:32Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [LangChain](<https://devfeed.tech/topics/langchain.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [DeepSeek Harness](<https://devfeed.tech/topics/dsh.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [building](<https://devfeed.tech/tags/building.md>), [company](<https://devfeed.tech/tags/company.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [harness](<https://devfeed.tech/tags/harness.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [marketing](<https://devfeed.tech/tags/marketing.md>), [sales](<https://devfeed.tech/tags/sales.md>), [teams](<https://devfeed.tech/tags/teams.md>)

### AI overview

LangChain's company harness combines five shared primitives: Slack-based access, identity-aware service actions, global and user-level memory, sandboxed code execution with authenticated service access, and scheduled or event-triggered runs. Its three agents apply these differently: OpenSWE uses the invoking user's GitHub identity for requests but its GitHub app identity for background reviews; GTM Agent uses fixed Salesforce credentials and user-authorized email available only in DMs; Content Studio uses user identity for Notion and company credentials for Twitter, with posting limited to whitelisted users. The agents run code in sandboxes connected through LangSmith's secret proxy. Slack supports direct messages, channel mentions, and breakout threads, while a custom UI handles larger email-review backlogs. The excerpt says memory can be global or user-specific and that this area remains underdeveloped. All three are built on Managed Deep Agents, which provides channels, crons, sandboxes, memory, and identity with room to customize behavior.

### Source excerpt

Learn how LangChain built internal agents across marketing, sales, and engineering, and how they have completely changed how those teams work.

## Context Engineering for AI Agents Starts with Retrieval

DevFeed: [Context Engineering for AI Agents Starts with Retrieval](<https://devfeed.tech/articles/context-engineering-for-ai-agents-starts-with-retrieval-97758.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/context-engineering-starts-with-retrieval>)

Author: LangChain Accounts

Published: 2026-10-23T17:19:57Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [context](<https://devfeed.tech/tags/context.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

The excerpt recommends giving agents only the information they need at each step. In LangChain's Deep Agents, `glob` searches filenames, `grep` finds exact text, and `read_file` reads pages in limited chunks; semantic retrieval is useful when wording varies, while SQL, search APIs, or MCP servers can serve other data needs. For oversized results, the harness can save content to files and return a preview and path. A custom retrieval tool can return paths directly, then subagents can read and summarize those files so the main agent receives key facts and sources. Freshness still requires current sources or date filtering, and retrieved text should be treated as untrusted and checked against expected sources. The excerpt presents these as ways to reduce wasted searches and context use, while noting that stale or irrelevant results can still mislead.

### Source excerpt

Agents waste time and context on clumsy searches, oversized results and stale data. Learn the retrieval techniques LangChain's Deep Agents harness uses to get the right context in.

## Ramp built an AI agent harness in six weeks -- and LangChain's CEO says it's part of a bigger shift

DevFeed: [Ramp built an AI agent harness in six weeks -- and LangChain's CEO says it's part of a bigger shift](<https://devfeed.tech/articles/ramp-built-an-ai-agent-harness-in-six-weeks-and-langchain-s-ceo-says-it-s-part-of-a-bigger-shift-95950.md>)

Original publisher: [Read original article](<https://thenewstack.io/ramp-laminar-agent-harness/>)

Author: Amanda Caswell

Published: 2026-10-22T16:31:15Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>)

Tags: [access-controls](<https://devfeed.tech/tags/access-controls.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agent-infrastructure](<https://devfeed.tech/tags/agent-infrastructure.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [async](<https://devfeed.tech/tags/async.md>), [asynchronous](<https://devfeed.tech/tags/asynchronous.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cloud-coding](<https://devfeed.tech/tags/cloud-coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [cost](<https://devfeed.tech/tags/cost.md>), [costs](<https://devfeed.tech/tags/costs.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [custom](<https://devfeed.tech/tags/custom.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [ramp](<https://devfeed.tech/tags/ramp.md>)

### AI overview

Ramp built Laminar, an internal harness now used across its agentic products, after months evaluating managed APIs, open-source frameworks, and third-party platforms. Its six-week first version combines execution, observability, sandboxing, and asynchronous workflows. Sessions and execution state stay separate from disposable sandboxes; credentials and orchestration remain outside them. A shared Connectors Service handles authentication, access controls, credentials, and tool execution. Ramp cites model flexibility, debugging visibility, and closer collaboration with product engineers as reasons to build in-house. LangChain CEO Harrison Chase praised several choices and says Deep Agents is pursuing similar sandbox, asynchronous-agent, and managed-connector capabilities. Separately, LangChain reports that routing models within Open SWE's harness across 973 threads reduced median LLM cost from $2.61 to $0.94, with no statistically significant difference in merged pull request rates. That experiment does not compare custom harnesses with existing frameworks. Ramp has published no operating-cost comparison; its harness still requires engineers to maintain and support it.

### Source excerpt

Ramp spent months testing managed agent APIs, open-source frameworks, and third-party platforms before concluding it would be better off building The post Ramp built an AI agent harness in six weeks -- and LangChain's CEO says it's part of a bigger shift appeared first on The New Stack.

## Powering the Agent Development Lifecycle with any framework, from ADK to LangChain and beyond

DevFeed: [Powering the Agent Development Lifecycle with any framework, from ADK to LangChain and beyond](<https://devfeed.tech/articles/powering-the-agent-development-lifecycle-with-any-framework-from-adk-to-langchain-and-beyond-93047.md>)

Original publisher: [Read original article](<https://developers.googleblog.com/powering-the-agent-development-lifecycle-with-any-framework-from-adk-to-langchain-and-beyond/>)

Author: Pier Paolo Ippolito; Elia Secchi

Published: 2026-10-21T17:37:47.402845Z

Content type: tutorial

Language: en

Sources: [Google Developers Blog](<https://devfeed.tech/sources/google-developers-blog.md>)

Topics: [LangChain](<https://devfeed.tech/topics/langchain.md>), [google-adk](<https://devfeed.tech/topics/google-adk.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [internal developer platform automation](<https://devfeed.tech/topics/internal-developer-platform-automation.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [observability](<https://devfeed.tech/topics/observability.md>), [versioning](<https://devfeed.tech/topics/versioning.md>), [qualitygates](<https://devfeed.tech/topics/qualitygates.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>)

Tags: [adk](<https://devfeed.tech/tags/adk.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-development-kit](<https://devfeed.tech/tags/agent-development-kit.md>), [agents](<https://devfeed.tech/tags/agents.md>), [bill](<https://devfeed.tech/tags/bill.md>), [can](<https://devfeed.tech/tags/can.md>), [cli](<https://devfeed.tech/tags/cli.md>), [custom](<https://devfeed.tech/tags/custom.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [developers](<https://devfeed.tech/tags/developers.md>), [development](<https://devfeed.tech/tags/development.md>), [development-kit](<https://devfeed.tech/tags/development-kit.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [extension](<https://devfeed.tech/tags/extension.md>), [extensions](<https://devfeed.tech/tags/extensions.md>), [framework](<https://devfeed.tech/tags/framework.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Agents CLI's experimental Extension System lets teams use other agent frameworks and customize command behavior while keeping the shared deployment and evaluation workflow. The first-party LangChain template in v1.8.0 scaffolds a project without `google-adk`; it replaces six commands, including `run`, `playground`, and `eval generate`. Two evaluation subcommands explicitly refuse because they require an ADK agent object. Deployment to Cloud Run and several other lifecycle commands remain native and framework agnostic; generated evaluations use the standard format consumed by native grading and comparison commands. Extensions can also wrap commands with organizational checks, as in the example that scans an SBOM before invoking native deploy. Extensions are distributed through Git, pinned to commit SHAs in a lockfile, and restored by `agents-cli install`; the project scope takes precedence over user scope. The system's manifest and command surface are experimental and may change incompatibly, so the text advises pinning the CLI version.

### Source excerpt

The Agents CLI Extension System enables developers to use frameworks like LangChain, LangGraph, or custom enterprise stacks while retaining a unified deployment and evaluation workflow. It details a first-party LangChain template that scaffolds, runs, and deploys agents without requiring the Agent Development Kit (ADK). Additionally, it demonstrates how platform teams can author custom extensions to enforce policies such as automated software bill of materials (SBOM) scans during deployment.

## Introducing PyDebeziumAI: Real-Time CDC for LangChain and LangGraph

DevFeed: [Introducing PyDebeziumAI: Real-Time CDC for LangChain and LangGraph](<https://devfeed.tech/articles/introducing-pydebeziumai-real-time-cdc-for-langchain-and-langgraph-89911.md>)

Original publisher: [Read original article](<https://debezium.io/blog/2026/10/19/introducing-pydebeziumai/>)

Author: Kodukulla Mohnish Mythreya

Published: 2026-10-19T00:00:00Z

Content type: release

Language: en

Sources: [Debezium](<https://devfeed.tech/sources/debezium-io.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Debezium Connector](<https://devfeed.tech/topics/debezium-connector.md>), [Snowflake streaming data architecture](<https://devfeed.tech/topics/snowflake-streaming-data-architecture.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>), [LanceDB vector database](<https://devfeed.tech/topics/lancedb-vector-database.md>), [software development triangle](<https://devfeed.tech/topics/software-development-triangle.md>)

Tags: [batch](<https://devfeed.tech/tags/batch.md>), [change-data-capture](<https://devfeed.tech/tags/change-data-capture.md>), [cron](<https://devfeed.tech/tags/cron.md>), [debezium](<https://devfeed.tech/tags/debezium.md>), [llm](<https://devfeed.tech/tags/llm.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval-augmented-generation-rag](<https://devfeed.tech/tags/retrieval-augmented-generation-rag.md>)

### AI overview

PyDebeziumAI is an open-source Python library that uses Debezium change data capture to keep vector stores synchronized with database changes for LangChain and LangGraph applications. It embeds Debezium in the Python process, compacts batched changes, and supports vector store adapters and retriever integrations. The article also describes a MySQL-to-Milvus example and reports benchmark latency in the low hundreds of milliseconds.

### Source excerpt

Retrieval-Augmented Generation (RAG) has become a central pattern in AI application development. The idea is simple: rather than relying solely on an LLM's pre-trained knowledge, you give it fresh context by retrieving relevant documents from a vector store at query time. But there is a catch that most tutorials skip over entirely. Where does that vector data come from, and how do you keep it current? Today, most teams answer that question with a cron job, a nightly batch reload, or a manual re-embedding script. That approach works until the database changes faster than the schedule runs, and your AI starts answering questions based on data that no longer exists or doesn't reflect a new record committed five minutes ago. This is the problem that PyDebeziumAI solves. It is an open-source Python library, developed as part of Google Summer of Code 2026 under the Debezium project, that wires Debezium's Change Data Capture engine directly into LangChain and LangGraph pipelines, ensuring your vector store updates the moment the database does. Read more...

## LangChain and LangGraph in Late 2026: What Is New and Who Should Use It

DevFeed: [LangChain and LangGraph in Late 2026: What Is New and Who Should Use It](<https://devfeed.tech/articles/langchain-and-langgraph-in-late-2026-what-is-new-and-who-should-use-it-89600.md>)

Original publisher: [Read original article](<https://www.developersdigest.tech/blog/langchain-langgraph-whats-new-2026>)

Author: Developers Digest

Published: 2026-10-17T00:00:00Z

Content type: article

Language: en

Sources: [Developers Digest](<https://devfeed.tech/sources/developers-digest.md>)

Topics: [LangChain](<https://devfeed.tech/topics/langchain.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>)

Tags: [agent-frameworks](<https://devfeed.tech/tags/agent-frameworks.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [langgraph](<https://devfeed.tech/tags/langgraph.md>)

### AI overview

LangChain 1.4 and LangGraph 1.2 added per-call approvals, built-in MCP, node timeouts, and DeltaChannel. The source summary says the article reviews changes shipped since May 2026 and considers who should use them.

### Source excerpt

LangChain 1.4 and LangGraph 1.2 added per-call approvals, built-in MCP, node timeouts and DeltaChannel. What shipped since May 2026 and who should pick it.

## October 2026 LangChain Newsletter: Everything we shipped at Interrupt NYC & London

DevFeed: [October 2026 LangChain Newsletter: Everything we shipped at Interrupt NYC & London](<https://devfeed.tech/articles/october-2026-langchain-newsletter-everything-we-shipped-at-interrupt-nyc-london-88047.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/october-2026-langchain-newsletter>)

Author: LangChain Accounts

Published: 2026-10-15T16:50:48Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [LangChain](<https://devfeed.tech/topics/langchain.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>)

Tags: [agent-evals](<https://devfeed.tech/tags/agent-evals.md>), [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-search](<https://devfeed.tech/tags/ai-search.md>), [custom-apps](<https://devfeed.tech/tags/custom-apps.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [v2](<https://devfeed.tech/tags/v2.md>)

### AI overview

The October 2026 LangChain newsletter highlights product releases from Interrupt NYC and London, including LangSmith AI Search, Managed Deep Agents v0.9, LangSmith Engine v2, trajectories, custom apps, and fine-tuning. It also covers LangChain v1.4.0, agent building with LangGraph, workshops, events, and a customer example involving Zip's chatbot and agent.

### Source excerpt

What we shipped at Interrupt NYC and London: LangSmith AI Search, Engine v2, Trajectories, Custom Apps, Fine-Tuning, and Managed Deep Agents v0.9.

## Building Long-Running Agents with ScaleDown and Deep Agents

DevFeed: [Building Long-Running Agents with ScaleDown and Deep Agents](<https://devfeed.tech/articles/building-long-running-agents-with-scaledown-and-deep-agents-86201.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/building-long-running-agents-with-scaledown-and-deep-agents>)

Author: LangChain Accounts

Published: 2026-10-13T14:01:24Z

Content type: tutorial

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [LangChain](<https://devfeed.tech/topics/langchain.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>)

Tags: [compression](<https://devfeed.tech/tags/compression.md>), [context-management](<https://devfeed.tech/tags/context-management.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [long-running-agents](<https://devfeed.tech/tags/long-running-agents.md>)

### AI overview

The article explains how to use ScaleDown constrained decoding models with LangChain and Deep Agents for long-running AI agents. It describes middleware for summarizing agent history, compressing tool results, extracting structured fields, and classifying agent state, plus integration with the LangSmith LLM Gateway. It presents ScaleDown-reported speed and cost comparisons for selected tasks and advises reserving general-purpose models for open-ended work.

### Source excerpt

Use ScaleDown's constrained decoding models with LangChain and Deep Agents to summarize history, compress tool results, and extract data faster and cheaper.

## What's New in Managed Deep Agents: schedules, per-run configuration, and Slack reactions

DevFeed: [What's New in Managed Deep Agents: schedules, per-run configuration, and Slack reactions](<https://devfeed.tech/articles/what-s-new-in-managed-deep-agents-schedules-per-run-configuration-and-slack-reactions-78337.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/managed-deep-agents-schedules-per-run-configuration-slack>)

Author: LangChain Accounts

Published: 2026-10-07T18:10:34Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [Slack](<https://devfeed.tech/topics/slack.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [managed](<https://devfeed.tech/tags/managed.md>), [schedules](<https://devfeed.tech/tags/schedules.md>), [slack](<https://devfeed.tech/tags/slack.md>)

### AI overview

Managed Deep Agents v0.9 adds agent-created reminders and recurring schedules, per-run configuration of models, skills, tools, and sandboxes, and configurable Slack reactions. The post describes how schedules inherit the originating channel and user permissions, while per-run configuration can tailor one deployment to different teams or repositories.

### Source excerpt

LangChain just released new capabilities in Managed Deep Agents. Agents can now schedule follow-ups, reconfigure themselves on every run, and react to Slack messages.

## Agentic retrieval with LangChain and Amazon Bedrock Knowledge Bases

DevFeed: [Agentic retrieval with LangChain and Amazon Bedrock Knowledge Bases](<https://devfeed.tech/articles/agentic-retrieval-with-langchain-and-amazon-bedrock-knowledge-bases-65179.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/agentic-retrieval-with-langchain-and-amazon-bedrock-knowledge-bases/>)

Author: Manideep Reddy Gillela

Published: 2026-10-05T15:53:56Z

Content type: tutorial

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-identity-and-access-management-iam](<https://devfeed.tech/tags/aws-identity-and-access-management-iam.md>), [aws-security-token-service](<https://devfeed.tech/tags/aws-security-token-service.md>), [costs](<https://devfeed.tech/tags/costs.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [rag](<https://devfeed.tech/tags/rag.md>), [run](<https://devfeed.tech/tags/run.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

This walkthrough builds a Retrieval Augmented Generation application using LangChain and Amazon Bedrock Managed Knowledge Bases. It compares standard single-shot retrieval with agentic retrieval, which plans sub-queries and can retrieve additional evidence for multi-part questions. Agentic retrieval can improve recall on complex queries but costs more and has higher latency; standard retrieval is cheaper and faster for short, well-scoped questions.

### Source excerpt

Build a Retrieval Augmented Generation (RAG) application on Amazon Bedrock Managed Knowledge Base with LangChain, and see how agentic retrieval handles the multi-part questions that single-shot retrieval answers poorly. Run the same query through both paths, read the trace events, and compare what each retrieval path costs.

## LangChain vs CrewAI: Orchestration Compared to OpenRouter-Native Routing

DevFeed: [LangChain vs CrewAI: Orchestration Compared to OpenRouter-Native Routing](<https://devfeed.tech/articles/langchain-vs-crewai-orchestration-compared-to-openrouter-native-routing-78617.md>)

Original publisher: [Read original article](<https://openrouter.ai/blog/insights/langchain-vs-crewai-orchestration-compared-to-openrouter-native-routing/>)

Author: OpenRouter

Published: 2026-10-02T00:00:00Z

Content type: comparison

Language: en

Sources: [OpenRouter](<https://devfeed.tech/sources/openrouter.md>)

Topics: [LangChain](<https://devfeed.tech/topics/langchain.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>)

Tags: [agent-framework](<https://devfeed.tech/tags/agent-framework.md>), [agent-frameworks](<https://devfeed.tech/tags/agent-frameworks.md>), [agent-sdk](<https://devfeed.tech/tags/agent-sdk.md>), [ai](<https://devfeed.tech/tags/ai.md>), [article](<https://devfeed.tech/tags/article.md>), [delegation](<https://devfeed.tech/tags/delegation.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [langgraph](<https://devfeed.tech/tags/langgraph.md>), [openrouter](<https://devfeed.tech/tags/openrouter.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>)

### AI overview

The article compares LangChain and LangGraph, CrewAI, OpenRouter-native model and provider routing, and OpenRouter's Agent SDK. It distinguishes workflow orchestration (planning, state, memory, and delegation) from selecting a model per call and selecting its provider. It recommends choosing among these tools according to whether an application needs orchestration, a bounded tool loop, or routing and fallbacks.

### Source excerpt

Multi-model orchestration is three layers. Workflow orchestration is planning, state, memory, and delegation, and LangGraph and CrewAI are built for it. Model routing is choosing a model per call and falling back when it fails, and provider routing is choosing which provider serves that model. OpenRouter does the second two. This article separates the layers, shows the same two-step pipeline in direct OpenRouter calls and in LangChain, and describes when to add a framework, when to use our Agent SDK, and how to put OpenRouter underneath LangGraph or CrewAI.

## Building ambient agents with Amazon Bedrock AgentCore: From event-driven signals to human-in-the-loop workflows

DevFeed: [Building ambient agents with Amazon Bedrock AgentCore: From event-driven signals to human-in-the-loop workflows](<https://devfeed.tech/articles/building-ambient-agents-with-amazon-bedrock-agentcore-from-event-driven-signals-to-human-in-the-loop-workflows-63580.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/building-ambient-agents-with-amazon-bedrock-agentcore-from-event-driven-signals-to-human-in-the-loop-workflows/>)

Author: Juan Albarran

Published: 2026-10-01T16:40:24Z

Content type: tutorial

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [Amazon DynamoDB](<https://devfeed.tech/topics/amazon-dynamodb.md>), [Amazon EventBridge](<https://devfeed.tech/topics/amazon-eventbridge.md>), [AWS Step Functions](<https://devfeed.tech/topics/aws-step-functions.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [amazon-sqs](<https://devfeed.tech/tags/amazon-sqs.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [dynamodb](<https://devfeed.tech/tags/dynamodb.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

This tutorial describes an event-driven pattern for ambient agents built on Amazon Bedrock AgentCore. It explains how S3 uploads and scheduled events can start agent jobs, how Lambda, SQS, and DynamoDB support the workflow, and how an ask_human tool pauses execution for review or approval before the agent resumes. The reference implementation includes a React interface for monitoring jobs and responding to requests, along with guidance on deployment, security, scaling, and extending the sample.

### Source excerpt

Ambient agents respond to events such as an Amazon S3 upload, a schedule, or an alert instead of waiting for a chat prompt. This post walks through building framework-agnostic ambient agents on Amazon Bedrock AgentCore using Amazon SQS, AWS Lambda, and Amazon DynamoDB, with a single ask_human tool and a Jobs page for human-in-the-loop review.

## Quiz: LLM Application Development With Python

DevFeed: [Quiz: LLM Application Development With Python](<https://devfeed.tech/articles/quiz-llm-application-development-with-python-61636.md>)

Original publisher: [Read original article](<https://realpython.com/quizzes/llm-application-development-python/>)

Author: Real Python

Published: 2026-09-29T12:00:00Z

Content type: article

Language: en

Sources: [Real Python](<https://devfeed.tech/sources/real-python.md>)

Topics: [Python](<https://devfeed.tech/topics/python.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [apis](<https://devfeed.tech/tags/apis.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [python](<https://devfeed.tech/tags/python.md>), [rag](<https://devfeed.tech/tags/rag.md>)

### AI overview

This 20-question quiz checks understanding of LLM application development with Python, including model APIs, prompting, LangChain, retrieval-augmented generation with embeddings and vector databases, AI agents, and the Model Context Protocol. It has no time limit and awards one point per correct answer, with a maximum score of 100%.

### Source excerpt

Test your grasp of building LLM apps in Python, from calling model APIs and prompting to RAG, AI agents, and MCP.

## Jev, One Week In: What TypeSafe AI's System One Model Actually Is, Every Real Use Case We Could Find, and the Open-Source Rival Already Chasing It

DevFeed: [Jev, One Week In: What TypeSafe AI's System One Model Actually Is, Every Real Use Case We Could Find, and the Open-Source Rival Already Chasing It](<https://devfeed.tech/articles/jev-one-week-in-what-typesafe-ai-s-system-one-model-actually-is-every-real-use-case-we-could-find-and-the-open-source-rival-already-chasing-it-58422.md>)

Original publisher: [Read original article](<https://ihatereading.in/blogs/jev-one-week-in-typesafe-ai-system-one-model-use-cases-laya>)

Author: Shrey Vijayvargiya

Published: 2026-09-22T17:30:00Z

Content type: comparison

Language: en

Sources: [iHateReading](<https://devfeed.tech/sources/ihatereading.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [API](<https://devfeed.tech/topics/api.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Transformer](<https://devfeed.tech/topics/transformer.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [JavaScript](<https://devfeed.tech/topics/javascript.md>), [Python](<https://devfeed.tech/topics/python.md>), [cURL](<https://devfeed.tech/topics/curl.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [api](<https://devfeed.tech/tags/api.md>), [backend](<https://devfeed.tech/tags/backend.md>), [blockchain](<https://devfeed.tech/tags/blockchain.md>), [coding](<https://devfeed.tech/tags/coding.md>), [development](<https://devfeed.tech/tags/development.md>), [frontend](<https://devfeed.tech/tags/frontend.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [jev-ai-model](<https://devfeed.tech/tags/jev-ai-model.md>), [jev-pricing-and-api](<https://devfeed.tech/tags/jev-pricing-and-api.md>), [jev-vs-llm-classifier](<https://devfeed.tech/tags/jev-vs-llm-classifier.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [laya](<https://devfeed.tech/tags/laya.md>), [laya-vs-jev-open-source](<https://devfeed.tech/tags/laya-vs-jev-open-source.md>), [llm](<https://devfeed.tech/tags/llm.md>), [model](<https://devfeed.tech/tags/model.md>), [node-js](<https://devfeed.tech/tags/node-js.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-ai](<https://devfeed.tech/tags/open-source-ai.md>), [product](<https://devfeed.tech/tags/product.md>), [programming](<https://devfeed.tech/tags/programming.md>), [python](<https://devfeed.tech/tags/python.md>), [react](<https://devfeed.tech/tags/react.md>), [review](<https://devfeed.tech/tags/review.md>), [system-one-ai-model-explained](<https://devfeed.tech/tags/system-one-ai-model-explained.md>), [system-one-models](<https://devfeed.tech/tags/system-one-models.md>), [typesafe-ai](<https://devfeed.tech/tags/typesafe-ai.md>), [typescript](<https://devfeed.tech/tags/typescript.md>), [web-development](<https://devfeed.tech/tags/web-development.md>), [what-is-jev-typesafe-ai](<https://devfeed.tech/tags/what-is-jev-typesafe-ai.md>)

### AI overview

A launch-week review examines TypeSafe AI's Jev, a System One model that answers predefined typed questions in parallel rather than generating text. It covers Jev's API, pricing, use cases, limitations, and the open-source Laya model that appeared shortly afterward.

### Source excerpt

What is the Jev AI model? A launch-week review of TypeSafe AI's System One model, pricing, API, real use cases, limitations, and open-source rival Laya.

[Next page](<https://devfeed.tech/topics/langchain.md?cursor=WyIyMDI2LTA5LTIyVDE3OjMwOjAwKzAwOjAwIiwgIjBhYzI5OWRkLWQ1OTgtNDI1ZC05MmVhLWFiZDYwOWFkYjE2NSJd>)