Langchain

Anthropic’s Claude Managed Agents raised the bar for managed agentic infrastructure when it launched earlier this week. LangChain’s response came fast: Deep Agents Deploy, now in beta, is a model-agnostic, open-source alternative that puts full memory ownership back in the developer’s hands. This is one of the more interesting competitive moves in the agent infrastructure space in recent memory — and if you’re evaluating where to build your production agent stack, you need to understand what’s actually on the table. ...

The hardest part of building AI agents isn’t getting them to work. It’s getting them to keep working well as requirements change, edge cases accumulate, and the gap between “passed our tests” and “performs in production” widens. LangChain thinks they have an answer. On April 8, 2026, the company open-sourced Better-Harness — a framework that treats evaluation data not just as a scorecard but as a training signal, using hill-climbing to autonomously optimize agent performance over time. ...

LangChain published a framework today for thinking about continual learning in AI agents — and it’s one of the clearest mental models for this problem that’s appeared in the wild. This guide takes that framework and turns it into a practical implementation playbook, with code examples for each layer and decision criteria for choosing between them. The three layers, briefly: agents can learn through context (runtime-injected instructions), storage (external memory), or weights (model fine-tuning). Each has different costs, speeds, and durability characteristics. ...

When developers talk about building AI agents that get smarter over time, they usually mean one of two very different things — and they rarely realize the ambiguity. LangChain’s Harrison Chase published a framework today that finally gives the field a shared vocabulary: continual learning for AI agents happens at three distinct layers, and conflating them leads to systems that are overbuilt for simple problems or structurally incapable of solving hard ones. ...

Full autonomy is the goal for many agentic workflows — but full autonomy is also where most production deployments fail their first risk review. The practical path to deploying AI agents in real organizations runs through human-in-the-loop (HITL) patterns: workflows where the agent does the work, humans approve the decisions, and the system handles the handoff cleanly. LangGraph has strong native support for HITL patterns through its interrupt primitives. This guide walks through the core patterns — interrupt points, approval gates, and reversible actions — with working code you can adapt for your own agent workflows. ...

LangSmith Fleet formalizes two agent authorization models: Assistants (on-behalf-of user credentials) and Claws (fixed service-account credentials). Picking the wrong one creates either security gaps or broken functionality. This guide helps you choose and implement correctly. For background on why this distinction matters, see: LangChain Formalizes Two-Tier Agent Authorization in LangSmith Fleet Decision Framework: Which Model Do You Need? Answer these questions before you write a line of config: 1. Does the agent access data that belongs to the individual user interacting with it? ...

One of the most consequential decisions in enterprise AI agent deployment is also one of the least discussed: should your agent act as the user, or as a service? LangChain’s Harrison Chase formalized this question in a March 23 post on “In the Loop,” LangChain’s developer newsletter, introducing the two-tier authorization model now available in LangSmith Fleet. The framework is called Assistants vs. Claws, and it directly addresses a security gap that enterprise teams have been quietly dealing with for months. ...

If you’ve tried to build a serious AI agent in 2025 or 2026, you’ve almost certainly hit the same wall: you pick a framework, go deep, and then discover you’re locked in. Want to move from LangChain to AutoGen? That’s not a refactor — that’s a rewrite. Choose Claude Code as your execution environment? Great, until you need to run the same agent in an OpenAI Assistants context. GitAgent is the project that calls this problem by its name and offers a structural solution: a framework-agnostic, git-native specification that lets you define an agent once and deploy it across any of the major orchestration layers without touching your core logic. ...

Building one AI agent is easy in 2026. Managing a fleet of them — keeping track of who they are, what they have access to, and whether they can be trusted to act without supervision — is the hard problem nobody talked about during the hype cycle. LangChain just shipped their answer. LangSmith Fleet launched on March 19, 2026 as an enterprise workspace for creating, deploying, and governing AI agents at scale. ...

LangChain has open-sourced Open SWE — a full software engineering agent framework built on LangGraph and their Deep Agents infrastructure — and it’s a meaningful step forward for teams who want to run coding agents that go beyond single-file edits into real, end-to-end software engineering workflows. The official release blog from LangChain dropped this week, following a preview post in January. The GitHub repository is live and active. What Open SWE Is Open SWE is an open-source framework for building and deploying internal coding agents — systems that can take a task description and see it through from understanding to implementation to pull request, running in a cloud sandbox environment along the way. ...