Install

Three steps, about two minutes. You install it, sign in, and connect it to your AI. Requires Python 3.10 or newer. Runs on Linux, macOS (Apple Silicon and Intel), and Windows through WSL2 (how). Native Windows is not supported.

Supported platforms

Sibyl Memory is built and tested on Linux and macOS (Apple Silicon and Intel). On Windows, run it inside WSL2: install Ubuntu from the Microsoft Store, open the Ubuntu terminal, and follow the Linux steps on this page. Native Windows (PowerShell or cmd) is not supported. If you already activated on native Windows, see Moving to WSL2 below.

1. Install it

Pick either one. Both install everything you need in one go.

Option A, with pip:

$ pip install 'sibyl-memory-cli[mcp]'

Option B, one-line installer:

$ curl -fsSL https://sibyllabs.org/install | sh

Both pull in the full toolkit: sibyl-memory-client (the local SDK), sibyl-memory-hermes (the Hermes provider), and sibyl-memory-mcp (the MCP server that sibyl setup wires into Claude Code and Codex). If you see an "externally managed environment" error, jump to If something did not work at the bottom for the one-time fix.

2. Sign in

Run this. It opens a sign-in page in your browser.

$ sibyl init

Sign in there with a wallet, or with your email and a code. The terminal picks it up on its own. An account is required: the memory tools do not run until this step has happened once on the computer. The free plan gives you the full memory system on one computer at no cost, no card needed. Credentials are written to ~/.sibyl-memory/credentials.json at mode 0600, next to this computer's signed access file, entitlement.json.

Have an account from the website?

Run sibyl init and choose Approve this computer on the page it opens. Sign in to your dashboard there if it asks, then type the six digit code from your terminal. The computer joins the account you already have, with its plan, instead of starting a new one.

Free is the default

You do not need to pay to build real things. Free tier gives you the full five-tier memory model with a 5 MB local cap on one computer. Pro lifts the cap, covers up to 2 computers, saves and debloats for you, and adds self-learning and the memory linter. See Tiers & access.

3. Connect it to your AI

This finds your AI app and connects Sibyl to it for you. No settings to edit.

$ sibyl setup

Then restart your AI app. That is it, Sibyl is connected.

It connects automatically to Claude Code, Codex, Hermes, and Cursor. If you use a different app, sibyl setup wires the ones it recognizes and prints a ready config block for the rest. Either way your AI can now save, recall, and search what it remembers. You can also name one target or preview the changes:

$ sibyl setup claude-code    # wire just one
$ sibyl setup --dry-run      # print what would change, write nothing

Targets: hermes, claude-code, codex, cursor, grokbot, deepseek. See Integrations for what each one does.

Your agent can install it for you

An agent with a shell (Grok Bot, a cloud coding agent, anything that runs commands) can do all of this itself. The installer needs no terminal prompts. Have it run curl -fsSL https://sibyllabs.org/install | sh, which wires what it finds, then sibyl setup --yes for anything added later (or sibyl setup grokbot on Grok Bot). The only step left for you is signing in. See Grok Bot.

4. Test it works

One command checks the whole path your agent uses, then cleans up after itself:

$ sibyl doctor

Open your AI and tell it something worth remembering, like: "remember that I like short, direct answers." Close it, open it again later, and ask: "how do I like my answers?" It will know. That is the whole thing, your AI remembers now.

Bring existing memory with you

Already have agent memory in CLAUDE.md, AGENTS.md, a Codex config, or Hermes files? sibyl migrate moves it in without risk. It backs up every file it finds and byte-verifies the copy before anything else happens, wires Sibyl into each detected harness, then prints a prompt you run in your own agent to extract structured memory from the backup. The extraction runs locally; Sibyl Labs never sees your files.

$ sibyl migrate
Installed before accounts were required?

Update, then connect to the internet once; setup finishes by itself. Memory you wrote before signing in moves into your account the first time a signed-in agent uses it. The details are on I installed before accounts were required.

Backup-first, never destructive

Trimming the originals is the last step, it is optional, and it only happens after you confirm and only because a verified backup already exists. Keep the backup until you have confirmed everything migrated.

Just the SDK

If you only want the library to call from your own Python:

$ pip install sibyl-memory-client

The SDK needs a signed-in account too: install sibyl-memory-cli and run sibyl init once on the computer. Without one, the client raises EntitlementError. Then jump to How it works for the API surface.

Verify

$ sibyl status     # local credentials, DB size, access, server-side tier
$ sibyl health     # provider self-check (schema version, DB path, tenant)

Windows: run it in WSL2

  1. Install WSL2 with Ubuntu: open PowerShell as Administrator and run wsl --install, then restart.
  2. Open the Ubuntu terminal and install Python if it is missing: sudo apt update && sudo apt install -y python3 python3-venv python3-pip.
  3. Follow steps 1 to 3 above inside that terminal. Claude Code, Codex, and Hermes running inside WSL2 are wired by sibyl setup the same way as on Linux.

Moving to WSL2 from native Windows

Your account lives on the server, not on the machine. Inside WSL2, run sibyl init and sign in with the same email or wallet; that adds a new computer to the same account. Free covers one computer, so sign the native-Windows install out first with sibyl devices revoke, or let sibyl init open the account page where you can sign it out. To bring your existing memory with you, copy the database into your WSL2 home:

$ cp /mnt/c/Users/<you>/.sibyl-memory/memory.db ~/.sibyl-memory/memory.db

Then run sibyl status and sibyl devices to confirm only the computers you use are signed in.

If something did not work

The steps above work for almost everyone. If the install showed an "externally managed environment" error, your system wants a sandbox first. These two lines make one and install Sibyl inside it:

$ python3 -m venv ~/.sibyl-memory/venv && source ~/.sibyl-memory/venv/bin/activate
$ pip install 'sibyl-memory-cli[mcp]'

Then carry on from Step 2 (sibyl init).

Connected nothing in Step 3? Make sure your AI app was open, then run sibyl setup again.

Installed on native Windows? That path is not supported; see Windows: run it in WSL2.