# RyanCodrai/turbovec

> A Rust vector index with Python bindings built on the TurboQuant algorithm for compressed embeddings and fast nearest-neighbor search without training.

- Magnitude: 0.9 out of 10 — Steady
- Stars: 17,397 total · +0 stars measured 2026-10-18, 00:28–10:31 UTC, ≈ 2 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Rust · License: MIT · Created: 2026-03-26 · Last push: 2026-10-07
- GitHub: https://github.com/RyanCodrai/turbovec · Homepage: https://pypi.org/project/turbovec/ · Page: https://gitnova.dev/en/r/RyanCodrai/turbovec

## Useful for

- Build a local RAG stack with private vector search and no managed services
- Speed up search over 10M documents by fitting the index in 4 GB RAM instead of 31 GB
- Filter search results by an allowlist from SQL or BM25 inside the SIMD kernel

## Why it’s here

- Star-counter measurements on 2026-10-18 (UTC), 00:28–10:31: 17397 → 17397 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +2 stars, using observed gains and the previous day.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1,488
- Issues and pull requests: 560
- Watchers: 75
- Average over the last week: 5 per day
- Usual pace: 14 per day

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 5, 1, 7, 7, 15, 35, 29, 9, 6, 11, 6, 8, 1, 7, 4, 6, 12, 5, 1, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-25 1.0, 10-06 2.2, 10-07 2.4, 10-08 1.6, 10-09 1.3, 10-10 1.5, 10-11 1.2, 10-12 1.4, 10-13 0.9, 10-14 1.3, 10-15 1.1, 10-16 1.2, 10-17 1.4, 10-18 1.0

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-18 10:33 UTC, updated every 30 minutes.