every agent you build or use, from a support bot to Grok Bot, Hermes or OpenClaw, can keep a memory of its own. what that memory is, the three ways to make one, and the film of it working. start here.
agent memory · step 1 of 8
every agent you build or use, from a support bot to Grok Bot, Hermes or OpenClaw, can keep a memory of its own. what that memory is, the three ways to make one, and the film of it working. start here.
an agent forgets. a support bot meets the same customer for the tenth time and asks their name again. a script that runs every morning starts from nothing every morning. a personal agent like Grok Bot, Hermes or OpenClaw learns how you work, then loses it when the session ends.
innernet gives each agent a memory of its own. it keeps what the agent needs to do its job, apart from every other agent and every tool, sorted by what kind of thing each piece is. and anything the agent learns about you comes to you first, and waits for your yes.

the short film shows three agents, each keeping its own memory. grok bot remembers that ana prefers email, and what she asked for last time. the rest of this chapter shows you how to do the same with yours, step by step.
you can make an agent from any of innernet's doors. they all make the same calls, so an agent you make in one shows up in the others straight away.
| the door | best when | the first move |
|---|---|---|
| the dashboard | you'd like to see it all as you go | agents → connect an agent |
| the terminal | your agent's code is in a folder on this machine | npx innernet agents new "support desk" |
| any chat | you'd rather just ask (Claude, ChatGPT, Cursor, Claude Code, Grok Bot) | "make me an agent called support desk" |
each one ends the same way. the agent gets a key, the key goes where the agent runs, and two small calls give it a memory: one before it answers, to bring back what it remembers, and one after, to keep what was worth keeping.

every memory says who it is about, and that decides where it may go.
all of it belongs to your account. an agent is never an account of its own.
.env.swipe the cards above, or press next at the foot of each step.
every chapter
innernet is memory your ai tools read live: every project, every decision, every skill, in one place, connected once.