The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
claude-code

Gamedev Toolkit for Claude Code Packages the Workflow, Not Just the Prompt

The first wave of coding-agent adoption was mostly prompt files and optimism. Put a CLAUDE.md in the repo, write down a few conventions, and hope the session remembers enough context to be useful. The new gamedev-toolkit-claude plugin is a small, niche project, but it points at the next phase:
16 May 2026 3 min read
claude-code

Lumo Turns Mobile UI Taste Into Deterministic Tools Claude Code Can Actually Call

Mobile UI review is one of the places where AI agents sound confident while being dangerously imprecise. A model can declare a screen “clean,” “modern,” or “accessible” without measuring a single contrast ratio or tap target. Lumo, a new Claude Code-compatible plugin and MCP package, is interesting because it pushes
16 May 2026 3 min read
MCP-Fence Wants to Make MCP Security Testable Before Your Agent Touches Production
claude-code

MCP-Fence Wants to Make MCP Security Testable Before Your Agent Touches Production

MCP security is getting past the blog-post phase and into the part that matters: tests you can run before an agent is allowed anywhere near production. That is the useful signal in mcp-fence, a new local-first scanner for Model Context Protocol servers. It is not famous yet. At research time
16 May 2026 4 min read
Qwen Code’s Preview Turns the CLI Into Agent Runtime Infrastructure
qwen

Qwen Code’s Preview Turns the CLI Into Agent Runtime Infrastructure

Qwen Code’s newest preview release is easy to misread as another fast-moving CLI changelog. That would miss the story. v0.15.12-preview.2 is Alibaba’s coding agent starting to behave less like a terminal toy and more like runtime infrastructure: daemon mode, workspace-scoped sessions, progressive MCP startup, worktree
16 May 2026 6 min read
OpenClaw’s Token Accounting Bug Turned Compaction Into a Per-Message Tax
openclaw

OpenClaw’s Token Accounting Bug Turned Compaction Into a Per-Message Tax

OpenClaw issue #82576 is a reminder that token accounting is not analytics garnish. In an agent runtime, token state drives compaction, compaction drives context continuity, and context continuity decides whether a long-running assistant feels reliable or starts shredding its own transcript every time someone sends a message. The bug is
16 May 2026 4 min read
OpenClaw’s Workspace Plugin Patch Shows Why Agent Extension Systems Need Defense in Depth
openclaw

OpenClaw’s Workspace Plugin Patch Shows Why Agent Extension Systems Need Defense in Depth

OpenClaw’s PR #82579 is the kind of security patch that almost nobody will tweet about and every serious agent platform needs. It does not add a model. It does not make an agent smarter. It tightens a loader seam where a disabled workspace channel plugin could still execute through
16 May 2026 4 min read
OpenClaw 2026.5.16-beta.2 Is a Runtime-Boundary Release, Not Just Another Beta Dump
openclaw

OpenClaw 2026.5.16-beta.2 Is a Runtime-Boundary Release, Not Just Another Beta Dump

OpenClaw’s v2026.5.16-beta.2 looks, at first glance, like another dense beta train: OAuth here, cron flags there, Telegram replay fixes, some Codex context-engine plumbing, a stack of malformed-state hardening. That framing misses the useful story. This release is less about features than about where OpenClaw now believes
16 May 2026 4 min read
Vera Rubin’s Real Pitch Is Predictable Agent Latency at Rack Scale
nvidia

Vera Rubin’s Real Pitch Is Predictable Agent Latency at Rack Scale

The headline numbers on NVIDIA’s Vera Rubin platform are large enough to make the usual launch-post immune system kick in: 3,600 PFLOPS of NVFP4 compute per rack, 20.7 TB of HBM4, 1.6 PB/s of memory bandwidth, and a roadmap claim of one-tenth the cost per
16 May 2026 5 min read
Dynamo Is NVIDIA’s Bet That Agent Inference Needs an API for Intent
nvidia

Dynamo Is NVIDIA’s Bet That Agent Inference Needs an API for Intent

NVIDIA’s Dynamo update is not interesting because it gives inference engineers another stack diagram to memorize. It is interesting because it admits the thing agent builders already know from staring at traces: an agent session is not a sequence of independent prompts. It is a long-running, stateful workload with
16 May 2026 5 min read
The UK’s Microsoft Probe Is Really About Whether Copilot Becomes the New Enterprise Default Setting.
azure-ai

The UK’s Microsoft Probe Is Really About Whether Copilot Becomes the New Enterprise Default Setting.

Copilot is no longer just another Microsoft 365 feature with a licensing page and a launch video. It is becoming the interface layer for enterprise work: the thing that reads the documents, watches the meetings, drafts the emails, touches the workflows, and increasingly mediates what employees can do with the
16 May 2026 5 min read
GitHub Just Removed Grok Code Fast From Copilot. That Says More Than a Changelog Should.
xai

GitHub Just Removed Grok Code Fast From Copilot. That Says More Than a Changelog Should.

GitHub did not merely remove a model from a dropdown. It removed xAI’s dedicated coding model from one of the most important distribution surfaces in software development — and did it on the same day xAI retired the same model slug in its own API. That timing is the story.
16 May 2026 5 min read
Microsoft Agent Governance Toolkit Moves Agent Security Into the Middleware Path Where It Belongs
ai-frameworks

Microsoft Agent Governance Toolkit Moves Agent Security Into the Middleware Path Where It Belongs

Agent security is finally moving out of the prompt and into the execution path. That is the important part of Microsoft’s new Agent Framework and Agent Governance Toolkit integration: not that Microsoft has another safety checklist, but that the policy decision happens before the agent acts, inside the runtime
16 May 2026 5 min read
← Newer Posts Page 94 of 136 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost