Learn Hyperagent
Core concepts and reference for working with Hyperagent.
Hyperagent is a platform for building AI agents that do real work. Not chatbots that answer questions and forget you. Agents with names, instructions, tools, knowledge, and multiple ways to start a run.
You configure an agent once. Then you use it across threads, trigger it from Slack, Telegram, email, a webhook, or an MCP client, schedule it on a timer, or let it watch for changes on its own. Everything it creates (documents, tables, webpages, images, videos, maps) lives in your Library and is searchable forever.
The platform learns with you. Skills let you teach reusable methods that any agent can pick up. Memories (global or agent-scoped) let agents remember what matters across every conversation. Rubrics measure whether your agents are actually getting better over time. Workspaces let colleagues use shared agents and knowledge with clear roles and ownership.
Where do you want to start?
I'm new to Hyperagent
The mental model, your first thread, your first agent, and where to put it to work.
Make my agent better
Teach it skills, build its memory, and measure quality with rubrics. This is where your agent starts learning with you.
Share in a workspace
Your agent works. Now others need it. Workspaces, sharing modes, and access control.
Configure an agent
Set its identity, tools, skills, knowledge, model, invocations, and autonomy.
Working with AI tools
Your agents and these docs are both built to be used by other AI tools, not just by people in a browser.
Invoke your agents from an MCP client
An external AI client, such as a coding agent, can start a thread with one of your agents and get the result back.
Feed these docs to an AI
Every page is served as plain Markdown: append .md to any docs URL, or use the Copy as Markdown button next to the breadcrumbs.
For AI readers: the documentation index is at /llms.txt and the complete documentation as one file is at /llms-full.txt.