LangChain adds browser control and background work to managed AI agents. LangChain's October 29 update adds browser tasks, human login handoff and background helpers, with shared-state tradeoffs and beta access requirements. Rohit Ramachandran October 29, 2026 LangChain's October 29, 2026 update adds browser control and background work to Managed Deep Agents. It gives teams building workplace assistants a way to handle website-only tasks and keep conversations moving during longer jobs. Developers can also use the browser to check web applications through their interfaces. This expands an existing developer platform, not a ready-made office assistant. Teams supply the instructions, tools and AI model; LangChain's LangSmith service runs the underlying software. The product remains in public beta. A browser for tasks without a software connection. The browser can navigate, click and fill in forms. But LangChain's browser guide recommends using a suitable API - a direct software connection - when one exists. For a business choosing what to automate, the useful starting point is the step that currently requires someone to use a website. For login or two-factor authentication, the assistant can hand the remote browser to a person to sign in on the website, not in chat, then return control. The agent cannot operate that window during the handoff, but sensitive page content may still be visible to it afterwards. Login sharing is a separate choice. By default, browser state belongs to one conversation and is shared by its authorized participants. An optional user setting carries an authenticated person's cookies and logins across their conversations. That saves repeated sign-ins, but logging out or switching accounts can affect their other conversations. Ending an agent run does not log the person out. Background helpers share files, not just results. Previously, a delegated task kept the main agent waiting. The new asynchronous subagents - background helpers with their own conversations - can work while the main agent continues talking to the user. It can check, redirect or cancel their work and receive completion notifications. The documentation says helpers running as the same user share the parent agent's sandbox, its working environment and files. Separate conversations therefore do not mean separate copies of a document. Teams delegating concurrent edits need to coordinate which files each helper can change. Approval handling also depends on the interface. Slack can show a helper's approval request in the original conversation; other channels require it to be handled in LangSmith Studio or through the API. A completed background task does not override an approval already holding up the main agent. The immediate gain is a more responsive conversation. These changes do not, by themselves, establish faster task completion or lower costs. What to check before adopting it. Deployment requires a workspace with Managed Deep Agents beta access. LangSmith's beta policy says interfaces and behavior may still change, and pricing is not necessarily final. The release announcement gives no date for general availability. LangSmith lists its Plus plan at US$39 per seat per month plus usage, including one small serverless deployment. Additional deployment and sandbox resources have usage charges. Teams also need model-provider access, so the seat price alone is not a complete budget for an assistant or a flat price per website task. Existing projects also face a migration. Version 0.10 removes the old MCP connector layout, used to connect agents to external tools. Those declarations must move to tools/mcp.py or tools/mcp.ts. The old sandbox scope setting is removed too; it is distinct from the new browser-sharing setting. For the related decision of how to build and try reusable workplace assistants, see RohitAI's coverage of Windmill's chat-based agent-building workflow.

Fetch.ai's new integrations could revolutionize AI agent. October 25th, 2026 Fetch.ai integrates with LangChain and Google Gemini, enhancing AI agent capabilities. Here's what this means for the future of AI development. Quick take. Summary is AI generated, newsroom reviewed. * Fetch.ai announces integration with LangChain and Google Gemini. * Community buzz surges as AI agent functionalities expand. * Traders monitor the implications for the broader crypto landscape. Sponsored: Coinfomania - Get your ad in the spotlight. Book your slot! Fetch.ai's recent tweet revealed collaborations with several high-profile tech platforms, including LangChain and Google Gemini. This move signifies a strategic effort to enhance the capabilities of AI agents within its ecosystem. As noted in the tweet, the integrations aim to provide developers with advanced tools, potentially reshaping the AI landscape in the crypto space. What happened. The broader crypto market is currently experiencing mixed signals, with varying momentum across different assets. Fetch.ai's announcement has sparked notable interest, especially among developers and tech enthusiasts, as it signifies a deeper engagement with existing platforms like LangChain and Google Gemini. By enabling AI agents to interface with these tools, Fetch.ai is positioning itself to capitalize on the growing demand for AI-driven solutions in blockchain technology. This integration may further enhance the functionality of AI agents, allowing them to perform more complex tasks while interacting seamlessly with payment systems like those from Stripe. Fetch.ai is a decentralized platform that aims to simplify the development of AI agents, providing a robust environment for creating intelligent applications. The collaborations with major tech players like LangChain and Google Gemini are poised to expand the capabilities of Fetch.ai's ecosystem, attracting further interest from developers looking to leverage AI in their projects. What comes next. Traders and developers should closely observe how these integrations develop and their potential impact on Fetch.ai's network. With increasing interest in AI and blockchain convergence, the market may see a shift in sentiment if Fetch.ai can successfully implement these partnerships. The growing community buzz around these integrations could also lead to increased trading activity as stakeholders assess their implications for the future.

Diagrid brings agentic durable execution to Goose. New Diagrid Catalyst integration for Goose, alongside support for LangChainGo, Mastra and other leading agent frameworks, lets agents survive crashes and resume at the last committed step on any Kubernetes cluster. Oct 23, 2026 Prev Next 1 of 43,839 Diagrid, developer of the world's most reliable foundation for mission-critical workflows and autonomous AI agents and the company behind the Distributed Application Runtime (Dapr), announced a new Diagrid Catalyst integration for Goose, an open source project hosted by the Agentic AI Foundation (AAIF), extending agentic durable execution to the open-source general-purpose AI agent, while also adding support for LangChainGo and Mastra. This release extends Catalyst's support to over 15 agent frameworks for Python, TypeScript, Java and C#. With Catalyst, a Goose recipe commits each step - every LLM call, extension tool call and sub-recipe invocation - before the next one begins. If the process or the node dies, the recipe resumes at the last committed step. Production agents run for minutes, hours or days. Containers are redeployed, nodes fail and API calls time out. Without durable execution, any of those events restarts the run from the beginning; every completed LLM call, tool call and API request executes again, and the organization pays for the same tokens twice. Catalyst commits each step before the next one begins, so when a process dies, the workflow resumes at the exact step that failed. Diagrid Catalyst adds durable execution underneath Goose recipes and subagents, so a long-running run resumes at the last committed step instead of restarting. Catalyst plugs into Goose through its standard extension mechanism, so no changes to Goose itself are required. Goose gives developers an open, extensible agent runtime that can operate through desktop, CLI and API interfaces, connect to external tools and systems through model context protocol (MCP) extensions and orchestrate work through reusable recipes and subagents. With Catalyst, a Goose recipe commits each step - every LLM call, extension tool call and sub-recipe invocation - before the next one begins. If the process or the node dies, the recipe resumes at the last committed step. Work already completed is not repeated and is not paid for twice. The result is a clean separation between the agent experience and the durability layer: developers keep Goose's recipes, sub-recipes, subagents and MCP extensions exactly as they are, and Catalyst supplies the execution durability beneath them. Added Support Built for Kubernetes Diagrid has also added integrations with LangChainGo and the TypeScript framework Mastra, bringing durable execution to organizations developing and deploying agents to Kubernetes backends. Some agent platforms tie durability to a single hosting environment, but Catalyst takes a different approach. It runs on Dapr, the Cloud Native Computing Foundation (CNCF)-graduated open-source project used in production at thousands of organizations, making agent workloads portable across AWS, Azure, Google Cloud and on-premises clusters. Teams avoid vendor lock-in, with no need to rewrite anything when they move. "Go and TypeScript agents on Kubernetes hit the same failure every long-running process hits: something breaks, and the work starts over," said Yaron Schneider, co-founder and CTO of Diagrid and chair of the Agentic AI Foundation Workflows Working Group. "These integrations let developers keep the framework they chose and gain a runtime that picks up where the agent stopped. And since Catalyst is built on Dapr, the same durability runs on any Kubernetes environment, in any cloud or on-premises."