/community/guides/agent memory
innernet
docsskillscommunitycompanydeveloperssecurityprivacytermscontact

agent memory · step 1 of 8

meet agent memory

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.

/community/guides/agent-memory
1 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 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.

your agents, round netti. each family of sub-agents sits beside the agent it works under
your agents, round netti. each family of sub-agents sits beside the agent it works under

watch it work

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.

agent memory, in a short film: muse, hermes and grok bot, each with a memory of its own

three ways in

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 doorbest whenthe first move
the dashboardyou'd like to see it all as you goagents → connect an agent
the terminalyour agent's code is in a folder on this machinenpx innernet agents new "support desk"
any chatyou'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.

one agent, three doors: the dashboard, the terminal and a chat all make the same thing
one agent, three doors: the dashboard, the terminal and a chat all make the same thing

what an agent keeps

every memory says who it is about, and that decides where it may go.

  • about the agent itself: how it does its job, its standing orders, what it knows about the world. this stays with the agent.
  • about the people it serves: each customer or user, named by your own id. this stays with the agent, never reaches you, and is forgotten in one call when someone asks.
  • about you: the person the agent belongs to. this is offered to your own memory, in the agent's voice, never yours, and only if you say yes.

all of it belongs to your account. an agent is never an account of its own.

the words worth knowing

  • key: the agent's password to its own memory. it reaches that one agent and nothing else of yours. it is shown once.
  • sub-agent: one job of an agent, split out (billing, say, or onboarding), with a memory and a key of its own.
  • access: what an agent may do with you. sealed, asks first (the default) or trusted.
  • waiting for you: something an agent learned about you. keep puts it in your memory, let go leaves it with the agent.

this chapter, step by step

  1. 1meet agent memory: you are here.
  2. 2make one on the dashboard: connect it, paste one block into your ai.
  3. 3make one from the terminal: one command, the key straight into .env.
  4. 4make one from any chat: ask, and try it before any code runs.
  5. 5wire it into your code: the two calls, in curl, typescript and python.
  6. 6your personal agents: Grok Bot, Muse, Hermes, OpenClaw and Instinct.
  7. 7what it may do with you: access, and what waits for your yes.
  8. 8see everything it keeps: its memory, its river, its keys and its sub-agents.

swipe the cards above, or press next at the foot of each step.



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