/community/guides/agent memory
innernet
docsskillscommunitycompanydeveloperssecurityprivacytermscontact

agent memory · step 7 of 8

what it may do with you

one choice decides how far an agent goes with you, sealed, asks first or trusted, and four lines say exactly what gets in and out. what it learns about you waits for your yes, and only you can give an agent more of you.

/community/guides/agent-memory-what-it-may-do
7 of 8
step 1 of 83 minmeet agent memoryevery 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.
step 2 of 83 minmake one on the dashboardthe easiest way in, even if you have never wired a memory before. connect an agent in the agents space, paste one block into the ai you code with, and watch it remember.
step 3 of 83 minmake one from the terminalone command in your agent's folder makes the agent and its key, puts the key straight into .env and keeps it out of git. then set what it may do with you, try it, and watch what it keeps, without leaving the terminal.
step 4 of 83 minmake one from any chatany ai connected to innernet can make and run your agents for you. say what you want in plain words, teach the agent one thing and ask it back before any code runs, and let a coding agent wire it in end to end.
step 5 of 84 minwire it into your codean agent's memory is two small calls, one before it answers and one after. here they are in curl, typescript and python, ready to copy, with the one rule for agents that talk to many people, and what comes back.
step 6 of 84 minyour personal agentsGrok Bot, Muse, Hermes, OpenClaw and Instinct, each on one memory. how to connect every one of them, what each can do once it's in, and how to give a personal agent a memory of its own.
step 7 of 83 minwhat it may do with youone choice decides how far an agent goes with you, sealed, asks first or trusted, and four lines say exactly what gets in and out. what it learns about you waits for your yes, and only you can give an agent more of you.
step 8 of 84 minsee everything it keepsan agent's memory is never a black box. its own page shows what it keeps, sorted by kind, every call it made, what its memory did for it, its keys, its sub-agents and the people it serves, and every setting is yours to change.

an agent keeps its own memory either way. access decides how far it goes with you: what it may read of your own memory, and what happens to what it learns about you.

one choice

open the agent, then access. it's one choice, its level:

levelwhat it reads of youwhat it learns about youwhat its answers carry
sealednothingstays with it. nothing reaches youits own memory only
asks first (the default)what any app you connect may readwaits for your yesits own memory only
trustedyour personal memoryis filed into your memory on its ownits own memory, and what it may read of you

an agent that works for other people never files anything about you from what they said. it stays with the person it came from.

its level, and four lines under it for what gets in and out
its level, and four lines under it for what gets in and out

four lines, if you'd like more say

under the level, four lines say exactly what gets in and out, each with a sentence of what the agent does now:

  • reads of you: nothing · like any app · personal · private too.
  • writes about you: never · asks first · freely.
  • takes in: sorted into memories · word for word.
  • hands out: its own memory · with what it reads of you.

set them by hand and the level reads your own mix. under finer choices, pick how private what it files about you is, and the parts of your life it may never write about (the people in your life, say).

what waits for your yes

when an agent that asks first learns something about you ("prefers replies after 10 am"), it doesn't go into your memory. it waits.

you'll find it in three places: the agent's activity → river, the agents list (inside the agent's row), and activity in the agents space, across every agent. each one has two buttons.

  • keep: it joins your own memory, in the agent's voice, marked as the agent's note. it never reads as something you said, and it never rewrites something you did say.
  • let go: it stays with the agent only. you won't be asked about the same thing again.
what an agent learned about you, waiting for keep or let go
what an agent learned about you, waiting for keep or let go

changed your mind? on the agent's access, under what it learned about you, take back pulls a kept thing out of your memory again, and send to you offers one that stayed with the agent.

only you can give an agent more of you

from the dashboard, a level applies at once. from anywhere else (the terminal, a chat, a key), sealed and asks first apply at once too. but trusted gives an agent more of you, so it comes back as a link.

open it, signed in, read the one sentence of what it asks for, and press say yes, or leave it as it is. the link lasts an hour, opens nothing for anyone else, and only works while the agent still stands where it stood when the link was made. no ai, no key and no agent can say yes for you.

a link only you can open: one sentence of what it asks, and your yes
a link only you can open: one sentence of what it asks, and your yes

a few things that are always true

  • an agent's key reaches that agent and nothing else: not another agent, not your projects, not your own memory directly.
  • a key, an app or the terminal can narrow what an agent reads of you on its own. never widen it.
  • every read of you is counted in the agent's ledger, against the key that made it, so you can see who read what.
  • removing an agent removes its memory, its keys and its ledger. what you kept from it stays yours.

next

see everything it keeps, and every call it made: see everything it keeps.



every chapter

the fundamentals5 guidesconnecting your ai5 guidesagent memory8 guidesthe dashboard4 guidesfor builders2 guidessharing3 guides

one memory, every ai tool.

innernet is memory your ai tools read live: every project, every decision, every skill, in one place, connected once.

start your innernetevery guide