Developers are replacing bloated MCP servers with Markdown skill files — cutting token costs by 100x. This article explores a two-layer architecture emerging in production AI systems, separating knowledge from execution. It details how skills (Markdown files) encode stable knowledge, while MCP servers handle runtime API interactions. The piece advocates for a layered approach to optimize context window usage, reduce costs, and improve agent reasoning by prioritizing knowledge representation in a version-controlled, accessible format.
This post reviews two LLM options in Emacs - Ellama and gptel - and how to set them up, including adding models from OpenRouter and Ollama.
Vercel has open-sourced bash-tool, a Bash execution engine for AI agents, enabling them to run filesystem-based commands to retrieve context for model prompts. It allows agents to handle large local contexts without embedding entire files, by running shell-style operations like find, grep, and jq.
Point at any URL or file. Get the gist. Fast CLI for summarizing anything you can point at: Web pages, YouTube links, Podcasts, Any audio/video, Remote files, Local files.
>The Playwright MCP Chrome Extension allows you to connect to pages in your existing browser and leverage the state of your default user profile. This means the AI assistant can interact with websites where you're already logged in, using your existing cookies, sessions, and browser state, providing a seamless experience without requiring separate authentication or setup.
The article explores whether combining a command-line agent (like Claude Code or Gemini CLI) with Unix-like file system tools and SemTools is sufficient for complex tasks, particularly document search. It details a benchmark testing the limits of coding agents with and without SemTools, focusing on search, cross-referencing, and temporal analysis. The conclusion is that CLI access is powerful and SemTools enhances agent capabilities for document search and RAG.
Interact with opencode server over HTTP. The `opencode serve` command runs a headless HTTP server that exposes an OpenAPI endpoint that an opencode client can use.
This article details how to set up an email triage system using Home Assistant and a local Large Language Model (LLM) to summarize and categorize incoming emails, reducing inbox clutter and improving email management. It covers the setup of a REST command to interface with Ollama, the automation process, and the benefits of using a local LLM for privacy.
We test out the latest product from Augment Code, a terminal app called Auggie CLI. How does it compare to other AI command-line interfaces?
- Workspace Indexing: Auggie automatically indexes the project directory, which is beneficial for context but raises security considerations (addressed via .augmentignore files).
Interactive vs. Non-Interactive Mode: The author tests both modes, highlighting the benefits of a one-shot, non-interactive command for quick tasks.
- Code Modification: A key test involves using Auggie to add Bootstrap classes to a Rails view file. Auggie successfully analyzed the existing code, generated a correct diff, and applied the changes.
- Workspace Indexing: Auggie automatically indexes the project directory, which is beneficial for context but raises security considerations (addressed via .augmentignore files).
Interactive vs. Non-Interactive Mode: The author tests both modes, highlighting the benefits of a one-shot, non-interactive command for quick tasks.
- Code Modification: A key test involves using Auggie to add Bootstrap classes to a Rails view file. Auggie successfully analyzed the existing code, generated a correct diff, and applied the changes.
A Model Context Protocol (MCP) server that provides tools for interacting with JMAP (JSON Meta Application Protocol) email servers. Built with Deno and using the jmap-jam client library.
