server-v0.0.4

opensandbox-group/OpenSandboxserver-v0.0.4Jul 10, 2026by Dhravya

AI Summary

The local supermemory instance now generates richer, more reliable memories and improves ingestion reliability. Users benefit from faster uploads, better file handling for PDFs and spreadsheets, and the ability to search memories within specific timeframes.

Key Highlights

Smarter memory generation for fuller, more useful results
Smoother ingestion pipeline with reduced queue times
Improved file handling for PDFs and spreadsheets
Time-aware search capabilities for specific periods
Richer profile organization with `/v4/profile`

New Features

Enhanced memory generation logic
Time-aware search functionality
Improved search ranking (inferred memories ranked lower)
Optimized ingestion reliability
Better profile API response structure

Full Release Notes

Your local supermemory instance now turns documents into richer, more reliable memories — and gets you to searchable results faster.

- **Smarter memory generation** — documents produce fuller, more useful memories from the content you add
- **Smoother ingestion** — uploads move through the pipeline more reliably, with less time stuck in queue
- **Better file handling** — PDFs and spreadsheets are handled more predictably on upload
- **Time-aware search** — ask about memories from "last week" or a specific period
- **Richer profiles** — `/v4/profile` returns organized memory buckets
- **Clearer search ranking** — inferred memories stay available but rank below your core memories

```sh
curl -fsSL https://supermemory.ai/install | bash
```

```sh
supermemory-server upgrade
```

Telemetry is optional — set `SUPERMEMORY_DISABLE_TELEMETRY=1` to turn it off completely.