The LGTM (Page 95)

The LGTM

Sign in Subscribe

LangChain Splits DeepAgents CLI From DeepAgents Code, and That Boundary Is the Product Strategy

LangChain Splits DeepAgents CLI From DeepAgents Code, and That Boundary Is the Product Strategy

LangChain’s deepagents-cli==0.1.0 release looks tiny until you read the removal notice. The package no longer ships the interactive TUI or coding-agent surface. It now keeps only deploy and supporting configuration, while users who depended on the chat REPL, sessions, MCP tooling, skills, and widgets are told

AI Middleware Is Becoming Critical Infrastructure, and MCP Is the Audit Boundary

AI Middleware Is Becoming Critical Infrastructure, and MCP Is the Audit Boundary

The phrase “AI middleware” sounds like something vendors invented to make plumbing billable. Unfortunately, it is also the right threat model. The dangerous layer in modern agent stacks is increasingly not the model itself, but the glue around it: model routers, MCP servers, plugin managers, tool proxies, local CLIs, background

Claude Code 2.1.143 Turns Plugin Dependencies and Background Sessions Into Things You Can Govern

Claude Code 2.1.143 Turns Plugin Dependencies and Background Sessions Into Things You Can Govern

Claude Code 2.1.143 is not the release that will make a launch video go viral. Good. The interesting work in coding agents right now is not another sparkling demo of a model editing five files at once. It is whether the runtime can survive plugin graphs, background workers,

OpenClaw’s Subagent Completion Regression Shows Multi-Agent Orchestration Is Still a Delivery Problem

OpenClaw’s Subagent Completion Regression Shows Multi-Agent Orchestration Is Still a Delivery Problem

Multi-agent orchestration is usually marketed as decomposition: split the work, spawn specialists, collect results. That story skips the part operators actually live with, which is delivery. A delegated task that finishes but never reports back is not automation. It is a very polite way to lose state. OpenClaw issue #82370,

OpenClaw’s Codex Harness Still Has to Prove Tool Policy Is a Runtime Boundary, Not a Config Wish

OpenClaw’s Codex Harness Still Has to Prove Tool Policy Is a Runtime Boundary, Not a Config Wish

There are two ways to ship a tool policy in an agent platform. One is as configuration: a tidy object, a feature flag, maybe a helper function with a reassuring test name. The other is as an actual runtime boundary: the exact place where the model tries to run bash,

Nemotron CLIMB Is NVIDIA Admitting the Expensive Part of Scaling Laws Needs Cheaper Test Fixtures

Nemotron CLIMB Is NVIDIA Admitting the Expensive Part of Scaling Laws Needs Cheaper Test Fixtures

The least glamorous way to save millions of dollars in AI is to find out your training recipe is bad before you run it at the size where the invoice becomes memorable. That is the real story behind NVIDIA’s Nemotron-CLIMB proxy models: two small base models, 62M and 350M