TurboQuant Memory

Compress and accelerate vector search in memory/RAG systems using TurboQuant (ICLR 2026) — near-optimal vector quantization with 5-8x compression and 98%+ se...

This skill mostly does what it says: local numpy-based quantization and migration of embeddings into a new SQLite table. Before running it on important data: (1) Back up any database you pass to migrate — the script creates a quantized_embeddings table and uses INSERT OR REPLACE which can overwrite rows. (2) Review the code locally: there are inconsistencies (SKILL.md/refs say blockwise Hadamard and warn against SRHT, but some modules/imports mention SRHTRotate or SRHT; some functions use type names like List/Dict without importing typing) — these may cause runtime errors or indicate the docs and code are out-of-sync. (3) Run the bundled tests (python3 scripts/turboquant.py) and validate on a small copy of your data (python3 scripts/validate.py --db /path/to/copy.db --auto-detect) to confirm behavior and metrics. (4) Prefer running migrate on a copied DB or staging environment. If you are not comfortable auditing Python code yourself, ask the author for clarification about the SRHT vs blockwise Hadamard mismatch and for guarantees about non-destructive migration and deterministic seeds.

Type: OpenClaw Skill Name: turboquant-memory Version: 2.0.0 The bundle provides a legitimate and well-implemented vector quantization tool based on the TurboQuant algorithm for compressing embeddings in SQLite-based RAG systems. The code (turboquant.py, memory_quantize.py, validate.py) performs mathematical transformations (Fast Walsh-Hadamard Transform, Lloyd-Max quantization) and database operations consistent with its stated purpose. It lacks any high-risk behaviors such as network access, shell execution, or data exfiltration. While the metadata and documentation contain future-dated references (e.g., ICLR 2026, arXiv 2025), the implementation is technically sound, transparent, and contains no evidence of malicious intent or prompt injection.