The Agent Audit Trail Format (AATF) is an open specification for recording why AI agents make decisions, including alternatives considered, confidence scores, and rejected options. It provides a struc…
A developer built an MCP server that charges AI agents per call using x402 micropayments, a protocol based on EIP-3009 that enables machine-to-machine payments without human sign-up. The server uses a…
OpenAI's 'Practical Guide to Building Agents' has sparked a debate with LangChain CEO Harrison Chase, who called it 'misguided' and published a detailed rebuttal. The conflict highlights a core tensio…
Arcade raised $60 million in a Series A round led by SYN Ventures, with participation from Morgan Stanley and Wipro, to secure AI agent access. The company provides an authorization platform for AI ag…
Google published a whitepaper co-written by Addy Osmani on the agentic software development lifecycle, detailing how agents function as a model plus a harness, with context engineering and verificatio…
A developer built contextcram, a zero-dependency Python library that prioritizes and packs context pieces (system prompts, chat history, documents) into a fixed token budget for LLM applications. It a…
LangChain.js provides a standardized framework for building LLM applications in TypeScript and Node.js, enabling developers to compose prompts, models, tools, and retrievers into reusable pipelines an…
An engineer built a LangChain agent that reads an inbox, summarizes threads, and drafts replies, but faced production issues with OAuth and privacy. The solution uses Nylas Agent Accounts to create a …
A comprehensive guide published in 2026 details 25 retrieval-augmented generation (RAG) strategies, organized into five pipeline layers, to help engineers and researchers move beyond naive RAG impleme…
A developer introduced a no-backend approach called "spotsocket" that lets users connect their own coding agents to webpages via a localhost WebSocket server, demonstrated with a kanban board controll…
LangChain co-founder Harrison Chase argues that AI agents can learn at three distinct layers—model, harness, and context—but most teams focus only on retraining the model. The harness layer, which opt…
AWS and LangChain released Deep Agents with Bedrock AgentCore, enabling developers to build context-rich research agents that delegate deep work to isolated subagents. The solution spawns specialized …
A new guide for cloud architects outlines practical steps to govern AI in the cloud, addressing the growing threat of shadow AI. The guide emphasizes discovery, data classification, and policy-as-code…
Nextbrowser, a cloud browser automation platform for AI-driven workflows, has been discontinued as of April 2026, while Browserbase remains active and has emerged as the leading alternative. Browserba…
Three vulnerabilities in LangGraph's checkpointer, disclosed on June 12, allow attackers to chain SQL injection into remote code execution on self-hosted servers using SQLite or Redis backends. The fl…
AgentBridge, an open-source Python project, provides a neutral mesh for translating, routing, verifying, and governing calls between different AI agent protocols, including MCP, A2A, ACP, OpenAI funct…
A developer built The Gauntlet, an open-source Next.js 16 app that connects seven MCP servers through a LangChain multi-agent pipeline and lets users toggle eight failure modes live during execution. …
Enterprise AI agents are expanding beyond server-side execution to operate directly in client runtimes such as browsers and desktop apps, enabling real-time interaction with unsaved data, UI state, an…
Valta has built a tool that enforces hard spending limits inside AI agents, blocking LLM calls before they exceed budget rather than relying on reactive account-level caps. The tool integrates nativel…
A developer built an AI agent using GPT-4o, the Browser-use library, and Playwright to automate healthcare tasks such as booking doctor appointments and downloading lab reports. The agent visually nav…