switch to 3ngram ·under 5 minutes · three starting points

3ngram imports what's already there — and captures everything from here.

whatever you're using to hold your context today — Claude Code MEMORY.md, ChatGPT / Claude exports, or nothing at all.

free · no card · we import, you verify, agents stay off until you flip them on.

switch ·we import, you verify

three starting points.

path 01 — from Claude Codemost common · ~3 min

we read your MEMORY.md and turn it into typed, searchable context.

Claude Code stores per-project memory at ~/.claude/projects/<slug>/memory/MEMORY.md. Upload a single file or a zip of the whole directory. Every top-level heading becomes a memory candidate you can review before anything is saved.

Claude Code export · .md or .zip · up to 50 MBget started free →
00:00export MEMORY.md (or zip the memory directory).00:40upload in Settings → Import.02:103ngram parses each heading into a memory candidate.03:00you review · import · agents stay off by default.
path 02 — from ChatGPT or Claudeconversation export · ~4 min

your flat chat history becomes typed — commitments with deadlines, decisions with rationale.

Export conversations.json from ChatGPT or Claude. 3ngram linearises each conversation and runs an LLM extraction pass that proposes memory candidates typed as preferences, decisions, or commitments. Nothing is written until you approve.

conversations.json · your tenant only · first 20 conversationsget started free →
00:00request export data from ChatGPT or Claude.00:30upload conversations.json — 3ngram types each memory.03:20review candidates · flag any re-typing.04:00nothing lost · everything now has shape.
path 03 — from nothingcold start · ~4 min

you have no shared work state yet, and that's fine. 3ngram starts capturing today.

The fastest path is the one with no import. Connect Claude / ChatGPT / Cursor / Codex via MCP, and your assistant calls remember as you work — the first time a decision, commitment, or preference worth keeping comes up, it's saved. Your first capture lands mid-session, not after it.

MCP server · every capture visible, revisable, deletablestart from zero →
00:00follow connecting clients in the docs (Claude Desktop · Cursor · Codex · Claude Code).01:00connect the client you already use.02:30keep working · your assistant calls remember when something worth keeping happens.04:00your first capture is in — recalled automatically next session.
switch ·defaults we think are sane

safety rails on day one.

agents are off by default.
capture runs. nothing sends. you flip on autonomous actions one verb at a time (draft, send, book, file).
safe
every connected source is read-only until you say otherwise.
3ngram cannot send from gmail, post in slack, or open a PR without a signed toggle in settings.
safe
nothing is mixed with other tenants' data in queries.
row-level security on every query, enforced at the database layer.
safe
imports are deduplicated by content hash.
imported Claude Code memory or chat export already in 3ngram? it won't land twice.
safe

onboarded in about four minutes. no card, no install.

prefer the full walkthrough? read the quickstart ↗ · connecting tools ↗

get started free ↵