47 items
41 posts, 6 tools
Most agent tool APIs are just REST endpoints with nicer names. Production agents need intent-shaped tools that compress workflows, reduce context, and return reviewable receipts.
Open Design is trending because it turns Claude Code, Codex, Cursor, Gemini, and other CLIs into a design engine. The useful lesson is not design automation. It is artifact-first agent wrappers.
A trending refusal-direction paper is a reminder that model safety cannot be treated as a thin refusal layer. Builders need layered controls around the model.
VS Code 1.118 makes Copilot a Git co-author by default for chat and agent commits. The argument is not really about one trailer line. It is about consent, audit signals, and who controls developer workflow metadata.
Agent runs are opaque. TraceTrail turns a Claude Code JSONL into a public share link with a stepped timeline of messages, tool calls, and tokens.
Claude Code hooks are powerful but discovery and install is a manual JSON-paste exercise. Hookyard is a directory plus CLI that makes it one command.
A curated directory of 312 Claude Code skills, plus Pro tools for authors who want analytics, version pinning, and a real submission flow.
The second half of our agent tooling release: distribution, validation, and ergonomics layered on top of the first six. Six small CLIs, one through-line.
Two quality-of-life tools we built this week for Claude Code daily drivers: a SKILL.md linter and a VS Code status bar that shows live LLM spend.
From Claude Code to Gladia, the ten CLIs every AI-native developer should know. Install commands, trade-offs, and when to reach for each.
Four agents, same tasks. Honest trade-offs from a developer shipping production apps with all of them.
A practical breakdown of GitHub Copilot Pro and Pro+ in 2026, focused on premium request economics, model access, and how to avoid request-burn surprises.
An opinionated guide to the MCP server ecosystem in 2026. Curated picks by category, real configuration examples, installation commands, and honest assessments of what works and what does not.
Visual testing tool for Model Context Protocol servers. Like Postman for MCP - call tools, browse resources, and view real-time logs in a browser UI. Zero install via npx.
Lightweight CLI for discovering and calling MCP servers. Dynamic tool discovery reduces token consumption from 47K to 400 tokens. Three subcommands: info, grep, call.
Centralized manager for MCP servers. Connect once to localhost:37373 and access all your servers through a single endpoint. REST API, web UI, and VS Code config compatible.
Registry and hosting platform for MCP servers. 6,000+ servers indexed. One-command install and configuration via CLI. Supports local and hosted deployments.
Largest MCP server directory with 17,000+ servers. Security grading (A/B/C/F), compatibility scoring, and install configs. ChatGPT-like UI for browsing and testing.
AI-powered terminal built in Rust with GPU rendering. Block-based output, natural language commands, Agent Mode for autonomous tasks. 700K+ developers. Free tier available.
One command, zero config. DD Traces is a local-first OpenTelemetry viewer for developers who use AI coding tools and want to see what happened.

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.