The LGTM (Page 30)

The LGTM

Sign in Subscribe

Agno 2.6.14 Makes Agent Memory Operable, Then Fixes the Gemini Race Waiting to Bite It

Agno 2.6.14 Makes Agent Memory Operable, Then Fixes the Gemini Race Waiting to Bite It

Agno 2.6.14 is a useful release because it refuses to treat agent memory like magic. The headline feature is CRUD for AgentOS learnings: list them, create them, fetch them, patch them, delete them, filter them, scope them, and enforce RBAC around them. That is exactly the right direction.

Antigravity Skills Show Where Coding Agents Are Heading: Less Tool Bloat, More Team Policy

The most important coding-agent feature of the month may be a directory with a Markdown file in it. That sounds like underselling it. It is not. Google’s updated Antigravity Skills material points at the part of agentic development that teams are finally being forced to operationalize: how do you

Gemini 3.5 Flash Is Google’s Coding-Agent Bet. The Benchmarks Are Good — and Messy.

Google wants Gemini 3.5 Flash to be read as a coding-agent model, not a cheaper chat model with a sporty name. That distinction matters. The new DeepMind model page does not lead with classroom benchmarks or conversational vibes; it leads with terminal coding, MCP workflows, UI control, finance agents,

Copilot CLI 1.0.62 Makes the Terminal Agent Look More Like a Workbench. That Comes With More Policy Surface.

Copilot CLI 1.0.62 Makes the Terminal Agent Look More Like a Workbench. That Comes With More Policy Surface.

Copilot CLI is no longer trying to be a polite chat window with a shell prompt nearby. GitHub’s 1.0.62-1 prerelease reads like a product manager swept half of GitHub’s daily workflow into the terminal agent: issue and pull request search, worktree creation, a richer diff UI,

Running Qwen Behind Claude Code Is the Local-Agent Wedge Alibaba Should Care About

Running Qwen Behind Claude Code Is the Local-Agent Wedge Alibaba Should Care About

The interesting part of the latest Qwen/Claude Code field guide is not that someone made a local model answer coding prompts. That stopped being novel somewhere around the third weekend everybody spent compiling llama.cpp. The useful part is more specific: a refreshed GitHub Gist shows what it actually

OpenClaw Subagents Reporting “Cancelled” While Still Running Is a Control-Plane Truthfulness Bug

OpenClaw Subagents Reporting “Cancelled” While Still Running Is a Control-Plane Truthfulness Bug

Multi-agent systems do not need cheerful status. They need truthful status. If work is waiting, say waiting. If it failed, say failed. If it was cancelled, reserve that word for actual cancellation. The moment an orchestration platform tells a user “Background task cancelled” while the subagent keeps running and eventually

OpenClaw’s `message_sending` Hook Bypass Is the Kind of Security Bug That Makes Extensions Look Safer Than They Are

OpenClaw’s `message_sending` Hook Bypass Is the Kind of Security Bug That Makes Extensions Look Safer Than They Are

A security hook that silently does not run is worse than no hook. No hook forces operators to be honest about the risk. A documented hook that appears installed, loaded, and available — while major delivery paths skip it — creates the kind of false confidence that gets secrets posted to channels

OpenClaw v2026.6.x Prompt Bloat Shows Why Agent Platforms Need Context Budgets, Not Just Bigger Models

OpenClaw v2026.6.x Prompt Bloat Shows Why Agent Platforms Need Context Budgets, Not Just Bigger Models

OpenClaw’s prompt-bloat report is a reminder that context windows are not RAM. You do not get to pour every tool description, channel hint, safety rule, UI affordance, and delegation policy into the front of a model run and call it “free” because the model advertises 128K tokens. The bill