Why We Built Bitweave: Sub-Millisecond Hybrid Retrieval in <1.1 MB RSS Memory

A developer built Bitweave, a zero-copy, SIMD-accelerated hybrid retrieval engine in Rust with Python bindings that handles categorical filtering and vector search while locking its active heap footprint under 1.1 MB RSS. Bitweave uses memory-mapped files and 1-bit vector quantization to achieve sub-millisecond latency on 200,000 records, outperforming JSON scans and SQLite in both memory and speed.

When building local RAG Retrieval-Augmented Generation applications, edge agents, or serverless AI pipelines, developers usually hit a wall with standard vector stores: memory overhead. Running a dedicated vector database locally often demands hundreds of megabytes—or gigabytes—of RAM just to keep indices warm. On the flip side, lightweight local options like scanning raw JSON files or querying SQLite don't scale well when vector dimensions climb into the thousands 1536d+ . We built Bitweave to solve this exact trade-off: a zero-copy, SIMD-accelerated hybrid retrieval engine in Rust with Python bindings that handles categorical filtering and vector search while locking its active heap footprint under 1.1 MB RSS. The Architecture: How Bitweave Achieves Sub-Millisecond Speed at <1.1 MB RAM Bitweave relies on a 3-part design to maximize search speed while keeping memory consumption negligible: Categorical Filters --- Bit-Sliced Bitmaps │ ▼ Query Vector 1536d -- 1-Bit SIMD Pre-Filtering Hamming Distance │ Top K Candidates ▼ Raw Embeddings Buffer - Zero-Copy Float32 Rescoring exact rescore=True │ ▼ Top-K Results Array NumPy Zero-Copy Memory Mapping memmap2 Instead of deserializing index files into Python RAM or Rust heap space, Bitweave uses memory-mapped files .bweave . The operating system's page cache handles lazy loading of index segments directly from disk into virtual address space. As a result, the active RSS memory footprint remains static around 1.1 MB, whether your index holds 5,000 or 200,000 records. 1-Bit Vector Quantization & SIMD Hamming Distance High-dimensional float32 vectors 1536d are quantized down to 1-bit sign masks where values 0 map to 1 and <= 0 map to 0 . During pre-ranking, Bitweave uses SIMD bitwise XOR and POPCNT operations to compute Hamming distances across candidate vectors in microseconds. Zero-Copy 2-Pass Float32 Rescoring exact rescore=True Quantization speeds up initial candidate selection, but full precision is critical for RAG accuracy. Bitweave solves this by taking the top N pre-ranked candidates and dereferencing their raw Float32 embeddings via direct offset pointers into a binary buffer. You get the speed of 1-bit SIMD filtering paired with exact float32 distance rescoring. Quick Benchmarks: 200,000 Records We benchmarked Bitweave against standard local retrieval approaches on a single machine processing 200,000 dense records: Python JSON Scan: ~450 MB RAM | 120 ms latency | ❌ No zero-copy SQLite Indexed : ~45 MB RAM | ~18 ms latency | ❌ No zero-copy Bitweave .bweave : ~1.1 MB RAM | < 1.0 ms latency | ✅ Zero-copy Getting Started with Python Bitweave is published on PyPI with pre-compiled wheels for Linux, macOS x86 64 & Apple Silicon , and Windows. Installation pip install bitweave Basic Usage python import numpy as np from bitweave import HybridIndex 1. Define schema and build index 1536-dimensional vectors schema = "category", "access" index = HybridIndex.builder schema, vector dim=1536 Add records doc id, metadata, embedding, external offset index.add record doc id=101, metadata={"category": "finance", "access": "public"}, embedding= 0.05 1536, external offset=0 index.save "my index.bweave" 2. Load index with zero-copy memory mapping loaded = HybridIndex.load "my index.bweave" 3. Perform 2-pass hybrid retrieval raw embeddings data = np.array 0.05 1536 , dtype=np.float32 .tobytes results = loaded.search filters={"category": "finance", "access": "public"}, query vector= 0.05 1536, top k=5, exact rescore=True, embeddings data=raw embeddings data Output is a zero-copy 2D NumPy array: doc id, score , ... print results Reproduce the Benchmarks Yourself We believe performance claims should always be independently verifiable. You can run the entire 200k benchmark suite and generate an interactive HTML report locally: git clone https://github.com/cteague2018/bitweave.git https://github.com/cteague2018/bitweave.git cd bitweave Setup environment & build Rust bindings python -m venv .venv source .venv/bin/activate Or .venv\Scripts\activate on Windows pip install maturin pytest numpy psutil maturin develop Run benchmark suite python benchmarks/run all.py Open report.html in your browser to inspect the latency distribution and RSS memory usage graphs.