Skip to content
All tags

#developer-tools

19 posts
ai deep-dive

Slack Code: Multiplayer AI Coding and the Agent Control Plane Landscape

Slack Code moves AI coding agents from individual terminals into shared Slack channels where teams can see diffs, previews, and plans in real time. But it solves management's visibility anxiety, not engineers' productivity bottleneck — the real battle is over who becomes the agent control plane.

TypeScript 7: A Native Go Rewrite Makes Type Checking Fast, but Migration Goes Beyond tsc

TypeScript 7 rewrites the compiler and language service in Go. The order-of-magnitude gains come from native execution and shared-memory parallelism, while old APIs and compiler options define the migration cost.

Exa: Neural Search Built for Agents, Not People

Exa turns every indexed web page into an embedding and retrieves by vector similarity instead of keyword matching. Official pricing as checked on 2026-08-21: $7 / 1k requests for /search (first 10 results included), $1 / 1k pages for /contents, $12–15 / 1k for the deep tiers, with $20 in free credits for new accounts. This blog's CLAUDE.md puts Exa first among cloud fetch tools, 16 of its 38 skills reference it directly, and only four existing posts mention it in passing — with zero dedicated posts. This is that post.

Reading Guide: Pick What Most People Use — the Other Five Criteria Are Tie-Breakers

The primary criterion has not changed: it is still adoption — and AI makes it matter more, not less, because more users means more training data means higher agent accuracy. The five criteria this series collects (machine-readable docs, types, whether the source is in your repo, data shape, machine-callability) are for breaking ties when adoption is comparable, or for costing out what picking the less popular option will charge you.

llms.txt: The Copy of Your Docs Written for Machines

llms.txt is a convention proposed by Jeremy Howard on 2024-09-03 (the spec is now at v2): a Markdown index at your site root written for LLMs. Hand-tested across six frontend docs sites: TanStack, shadcn, Zustand, AI SDK, and Next.js all ship it; React Router is the lone 404. The companion llms-full.txt (full-text version) is live at Anthropic, Cloudflare, and others. This post covers the spec, who uses it, and why it has started to influence library selection.

shadcn Registries and MCP: The Third Way to Distribute Components

Component distribution used to offer two roads: npm packages (black-box dependencies) or manual copy-paste. The shadcn registry standardizes a third — components described as JSON with embedded source and dependencies, installed by CLI straight into your repo as your own code. Anyone can host a registry (AI Elements is one), and the official MCP server lets AI agents browse and install components directly.

tech deep-dive

Three Routes to Hand-Drawn SVG Icons: A ~88k Free Library, a Generator That Bends Lucide, and the License Page Nobody Reads

Koboyo claims close to 90,000 free hand-drawn SVG icons (the count oscillates: 92,967 → 87,954 → 90,150), but its sitemap only lists about 17,930 icon pages, and its license page explicitly forbids building an icon library or canvas app with them. There are actually three routes to a hand-drawn look: collect a library, bend existing geometry programmatically (sketchyicons turns every straight run in Lucide into a quadratic Bézier, seeded by icon name for byte-for-byte reproducibility), or generate with AI. This piece compares seven libraries on scale and license, unpacks the algorithms behind sketchyicons and tldraw, and surveys the icon search tools now shipping MCP servers.

Choosing a Browser MCP: CDP, Playwright MCP, or Puppeteer MCP?

It's really a two-way choice now: @playwright/mcp (cross-browser, accessibility tree, token-cheap) versus chrome-devtools-mcp (Chrome's official server, performance and memory diagnostics). @modelcontextprotocol/server-puppeteer has been archived and is no longer a candidate. The dividing line is no longer abstraction level — it's 'drive the page' versus 'diagnose Chrome'.

@playwright/mcp: Microsoft's Official Browser Automation MCP Server

@playwright/mcp defaults to an accessibility tree (browser_snapshot) instead of screenshots, cutting token consumption sharply. Combined with Playwright's native auto-wait it's a sensible starting point for AI agents doing web automation — but note it now runs headed by default, keeps a persistent profile by default, and gates advanced tool groups behind --caps.

@modelcontextprotocol/server-puppeteer: The Official Puppeteer MCP Server

server-puppeteer is the Puppeteer wrapper in the official MCP servers monorepo — seven lean tools built around screenshots and evaluate. It has since been archived (moved to servers-archived, no longer published), so it is not a choice for new projects; if you want Puppeteer lineage in an MCP server today, look at the Chrome team's chrome-devtools-mcp.

tech deep-dive

Bumblebee: A Design Teardown of Perplexity's Read-Only Supply Chain Endpoint Scanner

A Go read-only scanner open-sourced by Perplexity in May 2026 (v0.1.1, zero non-stdlib dependencies). It inventories npm/PyPI/Go/RubyGems/Composer/MCP/editor and browser extensions into NDJSON, matches against a custom exposure catalog, and answers the question 'which machines in my fleet are currently affected' the moment a supply chain incident hits. It deliberately never invokes any package manager and is not an EDR.

Warp: From Modern Terminal to Agentic Development Environment

Warp evolved from a Rust-powered modern terminal into an AI Agent-integrated development environment (ADE), open-sourced under AGPL in April 2026, with over 700,000 developer users.

tech guide

Better Agent Terminal: Consolidate Multiple Project Terminals and Claude Code Agents into One Window

Better Agent Terminal (BAT) is an Electron desktop app that unifies multiple project workspaces, terminals, and Claude Code Agents into a single window — solving the everyday pain of exploding iTerm tabs and the lack of a proper GUI container for agents. MIT License, available on macOS, Windows, and Linux.

ai guide

oh-my-codex: A Structured Workflow Enhancement Layer on Top of OpenAI Codex CLI

oh-my-codex (OMX) doesn't replace Codex CLI — it adds a structured workflow layer on top of it. From requirements clarification and plan generation to multi-agent parallel execution, four core Skills transform scattered prompt conversations into a trackable development process.

From Stripe to Meta: How Silicon Valley's Top Companies Replace Keyboards with AI Agents

Top Silicon Valley companies are independently building internal AI coding agents that automate everything from a Slack message to a merged PR. This article deep-dives into architectures from Stripe, Ramp, Coinbase, and Spotify, then expands to cover Google, Meta, Amazon, Uber, Goldman Sachs, Walmart, and more.

tech guide

Where Should AI Agent Global Skills Live? The Division of Labor Between .claude, Codex Skills, and AGENTS.md

Skill paths are almost always runtime-specific. AGENTS.md is the reliable way to share rules across agents. Put personal reusable capabilities in each agent's supported global directory; put project workflows inside the repo.

tech guide

GitBook: A Documentation Platform That Turns Docs into a Product

GitBook is a Git-based documentation platform with Markdown editing, version control, and multi-user collaboration. Ideal for technical docs, API references, and internal knowledge bases. The free plan is sufficient for individuals and small teams.

tech guide

Documentation Platform Guide: GitBook, Docusaurus, Mintlify, and Seven Other Options

A breakdown of nine major documentation platforms — their positioning, pros, cons, and ideal use cases. Decision logic: open-source projects → Docusaurus/VitePress, API docs → Mintlify/ReadMe, internal enterprise → Confluence, fastest to launch → GitBook.

The Complete Guide to Agent CLIs: Design Logic, Tool Comparison, and Best Practices

Agent CLIs are not smarter autocomplete tools -- they are AI agents that can read your codebase, execute multi-step tasks, and operate in real environments. Claude Code, Codex CLI, Gemini CLI, OpenCode, Aider, Pi, Kiro, Amp, Cursor CLI... the tools keep multiplying, but they all share a common set of design principles -- understanding these principles is how you actually get good at using them.