Skip to content

Compose
Blog
Docs
About
Governance

An open registry where AI agents discover, compose, and invoke versioned, reviewed skills. Multi-provider, zero lock-in.

Platform

Catalog
Publish
Docs
API reference

Governance

Terms of Service
Privacy
Content policy
Takedown

Project

Changelog
Roadmap
License · Apache 2.0

© 2026 amitte · Apache 2.0 · content CC-BY-4.0set in Libre Franklin & IBM Plex Mono · next.js · tailwind · drizzle · hono

/blog

What we ship and what we're thinking about

Notes on skills, agents, MCP servers, trust tiers, and how to build with the registry.

All Skills Agents MCP servers Platform Tutorial

Tutorial
Shipping a bundle — skill + agent + MCP server in one publish
When you ship one skill, one agent, and one MCP server that all relate to the same problem, ship them together. Here is the wizard, and what it does under the hood.
May 2, 2026Read
Tutorial
BYOK compose — using your own API key end to end
Bring your own OpenAI / Anthropic / OpenRouter key, run /compose synchronously, and never let your key touch our database. Here is the data path.
May 2, 2026Read

First five minutes as a publisher — shipping your first skill

Sign in, write a manifest, paste a markdown body, click submit. The registry takes care of signing, versioning, and discovery.

May 2, 2026Read

First five minutes as a consumer — finding and running a skill

You have a goal. Someone has probably already published the skill that does it. Here is how to find theirs and skip writing your own.

May 2, 2026Read

Amitte in five minutes — what the product actually does

A guided tour of every surface, what each one is for, and the shortest path to seeing the value yourself.

May 2, 2026Read

Why Amitte exists — the open registry the agent ecosystem is missing

Every team writing AI agents is rebuilding the same prompts, tools, and connectors from scratch. Amitte is the npm-shaped layer that lets that work compound.

May 2, 2026Read

Trust tiers, signing, and why your verified badge matters

How the three tiers work, what verification requires, and why agents downstream can refuse to run unsigned content.

May 2, 2026Read

Multi-agent composition with /compose

Describe a goal, the registry searches existing skills, drafts the missing pieces, and hands you a publish-ready bundle. Here's the flow and what's actually happening underneath.

May 2, 2026Read

Connect an MCP server to Claude Desktop in 30 seconds

A two-step recipe — copy the snippet, restart Claude Desktop, you are done. Same pattern works for Cursor and VS Code.

May 2, 2026Read

Agents vs skills vs MCP servers — which one do I publish?

A practical decision guide. The three primitives sound similar but solve different problems; this is how to pick.

May 2, 2026Read

What is a skill, and why bundle one?

A skill is a verifiable, signed playbook an agent runs. Here is why they exist, what makes one good, and how the registry surfaces them.

May 2, 2026Read