
You've spent 1,000 hours talking to AI. Every decision, every “we tried X but it failed because Y” — gone. MemPalace keeps everything and makes it searchable.
Drop your conversations.json here
ChatGPT export · parsed locally · nothing leaves your browser
1. ChatGPT Settings → Data Controls → Export
2. Download zip from email, extract it
3. Find conversations.json and drop it above
Open source · MIT license · No API keys needed
MemPalace keeps every word. That's why it's 2x more accurate.
| MemPalace | Mem0 | Zep | ChatGPT Memory | |
|---|---|---|---|---|
| Recall accuracy | 96.6% | 49-85% | 63.8% | N/A |
| Monthly cost | $0 | $19-249 | $25+ | w/ subscription |
| Data location | Your machine | Cloud | Cloud | OpenAI |
| Information loss | Zero | High (AI extracts) | Medium | Extreme |
| Works with | Any LLM | API only | API only | GPT only |
$ claude mcp add mempalace https://mcp.mempalace.me/u/abc123
✓ Connected. 847 conversations · 12 wings · 67 rooms indexed.
--- next session ---
You: why did we choose JWT over sessions last month?
■ Found in wing_projectA / room_auth-architecture
2026-02-15 · Claude conversation · similarity: 0.94
“JWT gives us stateless auth across microservices. Session-based would require Redis for every service. The tradeoff is token revocation — we handle that with short expiry + refresh tokens.”
↑ verbatim from your original conversation. Not a summary. Not an AI extraction.
ChatGPT JSON, Claude exports, Slack. Auto-detect projects, people, topics.
Find by meaning, not keywords. ChromaDB embeddings, local, no API.
Entities, relationships, timelines. Auto-extracted, queryable, temporal.
Search, entity lookup, diary, navigation. Any MCP client, one URL.
30x token compression, zero info loss. 170 tokens to load months of context.
Your data never leaves your machine. MIT license. pip install mempalace.
Settings → Data Controls → Export. You get a zip via email. Upload conversations.json.
MemPalace runs 100% locally. No cloud, no API calls for search. Your data stays on your machine. Open source — audit every line.
Other tools spend compute on AI extraction (which loses info). MemPalace skips extraction and uses raw text + structure. Less compute, better results, $0.
Model Context Protocol — lets any AI tool access your memory. One URL connects Claude, ChatGPT, Cursor. 19 tools out of the box.
Engine: pip install mempalace (MIT). Web version Docker image coming. Or use mempalace.me for hosted access.
Upload your conversations. Give your AI a memory.
Free · Open source · MIT license · Your data stays yours