{"owner":"Firmamento-Technologies","github":"https://github.com/Firmamento-Technologies","claimed":false,"inventory":[],"indexed":[{"repo":"Firmamento-Technologies/TurboQuant","github":"https://github.com/Firmamento-Technologies/TurboQuant","description":"Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replacement","language":"Python","stars":20,"topics":["ann-search","approximate-nearest-neighbor","compression","deep-learning","embedding-compression","faiss","iclr-2026","information-retrieval","kv-cache","llm"],"license":"Apache-2.0","category":"machine-learning"}],"how_to_buy":"GET /r/Firmamento-Technologies/<repo> (Accept: application/json) for any listed repo here: tree, README, price and the checkout to pay (x402; rehearse first at its test twin, simulated money). Repos under 'indexed' are free: clone them from GitHub."}