ai-frameworks

A collection of 70 posts

LangGraph v1.1 Ships Type-Safe Streaming — LangSmith Agent Builder Becomes "Fleet"

LangChain's March 2026 newsletter landed tonight packed with significant updates across its entire product line. The headline release is LangGraph v1.1, which ships fully backwards-compatible type-safe streaming and invoke support alongside Pydantic and dataclass coercion — a change that closes one of the most persistent friction points for

01 Apr 2026 1 min read

ai-frameworks

Evaluating AI Agents in 2026: The Race Has Shifted from Capability to Reliability

G2 has introduced its first-ever "Best Agentic AI Software" awards category, and the timing says as much as the rankings do. The decision to create a dedicated evaluation framework for agentic systems — backed by a survey of over 1,000 business decision-makers — is itself a signal that the

01 Apr 2026 1 min read

ai-frameworks

MCP and A2A Are Becoming the Connective Tissue of Agentic AI

As multi-agent systems move from prototype to production, one of the most consequential architectural decisions a team makes is how their agents talk to each other — and to the tools they depend on. A new deep-dive in the Agentic Architectures series on DEV Community offers the clearest field guide published

01 Apr 2026 1 min read

ai-frameworks

AWS DevOps Agent Is Now Generally Available — Promising 75% Faster MTTR

AWS has moved its DevOps Agent from preview into general availability, marking a significant moment for agentic AI in enterprise operations. The agent operates as a fully autonomous SRE, capable of investigating incidents, correlating telemetry across observability stacks, runbooks, and CI/CD pipelines, and proactively flagging the conditions that precede

01 Apr 2026 1 min read

ai-frameworks

DataCamp & LangChain Launch AI Engineering Learning Track for Builders

DataCamp and LangChain have announced a formal partnership to launch a structured AI Engineering learning track, designed to teach developers how to build and deploy production-grade AI applications using the LangChain framework. The curriculum targets the widening gap between teams that can prototype with LLMs and teams that can actually

31 Mar 2026 1 min read

ai-frameworks

Agentic Harness Engineering — Why the System Around the LLM Matters More Than the Model

A practitioner building a production financial AI assistant has published one of the more honest post-mortems on the AI framework hype cycle: the framework wasn't the problem, and switching it wasn't the fix. After struggling with a complex stack of LlamaIndex, MCP integrations, and elaborate RAG

31 Mar 2026 1 min read

ai-frameworks

Opera Neon Goes All-In on Agentic Browsing with Native MCP Support

Opera Neon has taken a significant step toward making the browser a first-class citizen in the agentic AI ecosystem, rolling out native support for the Model Context Protocol (MCP) directly inside the browser. With the update, users can connect AI tools — including ChatGPT, Claude, and Gemini — to their live browsing

31 Mar 2026 1 min read

ai-frameworks

Microsoft Drops Comprehensive Agentic AI Security Framework for Copilot & Agent 365

Microsoft's March 2026 security guidance marks a meaningful shift in how the company — and likely the broader enterprise software industry — frames agentic AI. Rather than treating autonomous agents as a productivity feature bolted onto existing infrastructure, the framework positions them as a security architecture challenge that demands its

31 Mar 2026 1 min read

ai-frameworks

MCP Is a Great Start — But Multi-Agent Production Needs More

The Model Context Protocol has done a lot of heavy lifting to connect AI agents to the tools they need, but a developer deep-dive published on DEV Community reveals where MCP runs out of road in real production systems: shared state. When multiple agents — built with LangChain, AutoGen, CrewAI, or

31 Mar 2026 1 min read

ai-frameworks

AWS Launches "Agent Plugin for AWS Serverless" — MCP Servers + Sub-Agents in One Modular Unit for Claude Code, Cursor, and Kiro

AWS quietly introduced one of the more interesting packaging abstractions in the agentic tooling space this week: the Agent Plugin for AWS Serverless. The plugin bundles skills, sub-agents, and MCP servers into a single modular unit that auto-loads into AI coding assistants — currently supporting Claude Code, Cursor, and Amazon'

30 Mar 2026 1 min read

ai-frameworks

Google ADK for Java 1.0.0 GA: A2A Protocol, Human-in-the-Loop, and Centralized Guardrail Plugins

Google's Agent Development Kit for Java has reached its 1.0.0 general availability release, and it arrives with a set of capabilities that signal the framework is ready for serious enterprise workloads. The headline addition is native Agent2Agent (A2A) protocol support, which lets Java-built ADK agents collaborate

30 Mar 2026 1 min read

ai-frameworks

7 RAG Deals Reshaping How Enterprise AI Accesses Data

A quiet but consequential shift is underway in how enterprise RAG systems get built: legal data access has become the binding constraint, and it is now outpacing the purely technical challenges of retrieval. A new analysis from RAG About It maps seven active licensing deals reshaping how enterprise AI pipelines

30 Mar 2026 1 min read

← Newer Posts Page 3 of 6 Older Posts →