Skip to main content
By the end of this guide, Claude Code will start each session oriented with your open work, surface relevant memories before it edits files, and let you save and recall typed memories from any session. There are two layers, and you can stop after the first:
  1. MCP connection (OAuth) — the remember, search, and briefing tools, available inside a session.
  2. Hooks (API key) — a read-side context feed. The SessionStart briefing injects your open work into the model’s context at the start of every session; an optional PreToolUse precheck runs before edits. Both are fire-and-forget so they never block you.

​
Prerequisites

  • A 3ngram account — the email and password you use for the dashboard at https://app.3ngram.ai.
  • Claude Code installed and signed in.

​
Layer 1 — Connect over MCP

1

Add the server

claude mcp add --transport http 3ngram https://mcp.3ngram.ai/mcp
2

Authenticate

Run /mcp inside a session and pick 3ngram. A browser opens the 3ngram consent page; sign in, check the redirect host, and approve the two scopes (memory:read, memory:write). The client registers itself and stores a rotating refresh token — you will not sign in again until the grant is revoked. See the Quickstart for the full OAuth walkthrough.
3

Save your first memory

In a session, ask Claude Code:
Remember that we decided to use Postgres full-text search instead of
Elasticsearch for the v1 search backend.
It calls remember, appending a typed decision to your default scope. Writes never overwrite — see Memory model.

​
Layer 2 — Add the hooks

The hooks are a small static binary, 3ngram-hook, that reads from the REST API so each Claude Code session starts with context. They are read-only: high-value write capture stays with the remember tool and the /debrief skill, never a mechanical hook.
1

Install the binary

Download the prebuilt 3ngram-hook for your platform from GitHub Releases, verify its sha256 against checksums.txt, and place it on your PATH.
3ngram-hook --version
2

Create an API key

In the dashboard, open Settings → API keys and create a key. The full key is shown once, in the form 3ng_<prefix>_<secret>. Copy it immediately.
3

Give the hook the key

Either export it in your shell profile or the env block of ~/.claude/settings.json:
export THREENGRAM_API_KEY=3ng_<prefix>_<secret>
or write it to ~/.config/3ngram/api-key (one line, no quotes). The hook talks to the REST API at https://api.3ngram.ai by default, so no host configuration is needed.
4

Wire the hook events

Add the SessionStart briefing to ~/.claude/settings.json. Its output is injected into the model’s context at the start of every session:
{
  "hooks": {
    "SessionStart": [
      { "hooks": [{ "type": "command", "command": "3ngram-hook briefing" }] }
    ]
  }
}
You can also wire 3ngram-hook precheck to PreToolUse (matcher Write|Edit) to look up related memories before edits. In current Claude Code its output appears in the hook transcript (view with Ctrl-R) rather than being injected into the model’s context automatically — PreToolUse plain stdout is not added as context the way SessionStart is. Treat precheck as a diagnostic aid, not a guaranteed model-visible feed.
By default the briefing orients by the current project when you are in a git checkout, and falls back to your whole account otherwise. To orient from a specific scope instead, set both env vars: THREENGRAM_BRIEFING_KIND=scope and THREENGRAM_SCOPE=work. Setting THREENGRAM_SCOPE alone has no effect unless the kind is scope.
5

Verify the pipeline

3ngram-hook verify
#   API base: https://api.3ngram.ai
#   API key:  3ng_abcd… (N chars)
#   briefing: 200
# OK — briefing pipeline is configured.
Exit code 0 means configured and reachable. 1 means no key was found; 2 means the key was rejected or the service was unreachable.

​
Confirm capture and recall across sessions

1

Capture in one session

Ask Claude Code to remember a decision (Layer 1). Confirm it landed:
Search your memory for the v1 search backend decision.
search returns the memory you just saved.
2

Recall in a new session

Quit and start a fresh Claude Code session, then ask the same search question. The memory is still there — that is the cross-session proof, and search finds it regardless of scope or project.The SessionStart briefing also runs automatically, but it is scoped: inside a git checkout it orients by the current project, so it surfaces this memory only if you saved it with that project. To see unscoped memories in the briefing, capture them with a project, or set THREENGRAM_BRIEFING_KIND=all (or scope) as covered above.
You now have memory that outlives the session. Next: connect your other tools in Connect other tools, or learn what makes recall trustworthy in Recall and supersession.