Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The post frames model routing — not prompting — as the primary productivity lever in Claude Code, and provides a concrete cost-and-capability breakdown of five distinct models that developers must now choose between for every task.
slash-agent removes the need for a persistent background process to get LLM assistance in the terminal, making AI coding help available on-demand with zero idle resource cost and full support for local private models.
The release resolves multiple Agent Manager stability regressions — including a webview blanking bug and startup conflicts with other VS Code extensions — while the BYOK badge makes key-routing transparency visible directly in the model selector.
Gora removes the per-session rediscovery overhead and preserves chat history that would otherwise be lost when Codex and Claude Code hit their local chat limits.
The Amp plugin approach reduces specialized agent creation to a small, self-contained configuration that Amp can generate on its own.
Surface extends coding agents beyond the text channel by giving them the ability to autonomously build, serve, and react to structured HTML interfaces — removing the back-and-forth of chat for tasks that benefit from richer UI interaction.
A hands-on test of 74 MCP servers across two major agentic coding clients in isolated microVM environments.
Record & Replay removes the need to manually re-describe recurring workflows in prompts by encoding a user's demonstrated process and preferences into a persistent, reusable skill.
The benchmark exposes that current coding agents collapse within 5–6 turns on sustained multi-turn tasks — a failure mode invisible to single-task fraction-of-tasks-solved metrics — and quantifies that test feedback and harness choice are the dominant levers for improvement.
AI DevKit addresses the orchestration gap that emerges when developers run multiple coding agents simultaneously — shared config, memory, messaging, and verification are handled at the control-plane level rather than manually across scattered terminal sessions.