Tagged: agents
Pages with this tag
Mastra
1The TypeScript agent framework — agents, tools, workflows, memory, RAG, eval, and observability, built on top of the Vercel AI SDK. Start here for the mental model, then go deep.
Building agents
2The minimal end-to-end path — define a tool, define an agent, register it on the Mastra instance, and call it from your app.
Multi-agent systems
3When one agent isn't enough — a supervisor agent that delegates to specialist sub-agents, plus the other coordination patterns.
Phase 1 · Set up the AI dev environment
4Stand up the agent operating system for a CodeCanyon Laravel app — the constitution, permission modes, rules, skills, and IDE wiring that every later phase relies on.
AI writing contract
5Binding rules for Cursor, Claude, Codex, and other agents authoring ZajLibrary docs — voice, editorial color, plugin mechanics, and mandatory visuals.
Authoring & agents
6Agent-facing digests for voice, plugins, intake, and QC — always verify against AGENTS.md and code truth.
Use local ZajLibrary MCP
7Run zajlibrary-local on port 4321 — when to prefer local over prod, dev setup, index refresh, CodeCanyon playbook QA, and testing submit_feedback on the dev queue.
Use the ZajLibrary MCP
8Connect Cursor or Claude Code to ZajLibrary at /api/mcp — endpoints, tools, auth scopes, feedback, admin triage, smoke test, and a reliable search-then-read workflow for agents.
AI Coding Agent Setup Reference
9A reusable catalog for configuring AI coding agents — MCP, Skills, Subagents, Slash Commands, Hooks, Plugins, Rules, and memory — across Claude Code, Cursor, Codex, and Windsurf.