Conservative writing signals
Your history, made navigable
Find the questions, facts, and ideas you keep returning to.
Choose your ChatGPT export. Memory Map reads its conversation files in this tab, then builds a searchable semantic graph with a browser-loaded embedding model.
- 1ParseRead split conversation files one at a time.
- 2MapEmbed bounded prompts and fact candidates.
- 3ExploreSearch, inspect repeats, and trace every result.
Private by construction.No upload endpoint, account, analytics payload, or archive persistence. Model files download from Hugging Face; your conversation text is not sent with that request.
Reading archive
Building your memory map
Inspecting ZIP entries…
Statistics appear before embeddings finish. The first semantic run downloads and caches a small model in your browser.
Route interrupted
This archive could not be mapped.
Mapped memory
Your conversation history, connected.
Network scale
Overview
Things connected by meaning
Topic map
Node size is conversation count. Lines are semantic proximity.
Semantic map is still forming.Deterministic insights are ready below.
Focused neighborhood · the complete topic list follows.
Different ways to read the archive
Question lenses
Queries may appear in more than one domain. Open any result to inspect its supporting conversations.
0
Conversations that changed tracks
Likely thread changes
Interchange patterns
Questions you return to
Exact wording and semantic repeats are kept distinct.
Prompts from your own evidence
Questions your history asks you
Invitations to review a repeat, correction, old memory, quiet theme, or wording spike—not conclusions about you.
Wording, not personality
Query tone
A more expressive vocabulary
Language signals in your queries
Cadence over time
Rhythms
How the map was made
Transparent by default.
Statistics, question lenses, typo and thread-change candidates, query tone, language signals, and reflection prompts use local, inspectable rules. Topic relationships, semantic repeats, fact grouping, and search use normalized MiniLM embeddings.
Assistant assertions are excluded from the fact ledger. Large histories are sampled for semantic work while totals continue to cover the full parsed export.