ruvnet / ruvector-finger-overview.md

Created April 27, 2026 07:32

ruvector FINGER 2026: First Rust implementation of FINGER graph ANN approximate distance skipping (arXiv:2206.11408) — 80% prune rate, 2x QPS on high-dim embeddings, zero unsafe

ruvector 2026: FINGER — High-Performance Rust Graph ANN with Approximate Distance Skipping

150-char summary: First production Rust impl of FINGER (WWW 2023) — skips 80%+ of graph ANN distance computations using precomputed residual bases, reducing per-query cost in vector search pipelines.

Introduction

Modern vector databases — Qdrant, Milvus, Weaviate, Pinecone — all rely on graph-based approximate nearest neighbor (ANN) algorithms like HNSW. The shared bottleneck: every graph edge traversal requires an O(D) exact distance computation against a D-dimensional embedding. At D=128 (SIFT, visual features) or D=1536 (GPT-4 text embeddings), over 80% of these computations are wasted — the neighbor is too far to ever enter the top-k result set.

FINGER (Chen et al., WWW 2023, arXiv:2206.11408) solves this by precomputing a K-dimensional orthonormal basis from each graph node's edge-residual vectors at build time. During beam search, it projects the query residual onto this K-dimensional subspace o

ruvnet / 16-ghost-murmur-ruview-spec.md

Created April 26, 2026 21:40

Ghost Murmur on RuView: open-source spec for an honest, multi-modal heartbeat mesh (60 GHz mmWave + WiFi CSI + NV-diamond simulator). Reality-checks the April 2026 CIA news against published physics and shows what an open-source 65 build looks like.

Ghost Murmur on RuView — A Specification for an Open, Honest, Multi-Modal Heartbeat Mesh

SOTA Research + Build Spec — Quantum Sensing Series (16/—)

Field	Value
Date	2026-04-26
Domain	NV-diamond magnetometry × 60 GHz mmWave radar × WiFi CSI × multistatic fusion
Status	Research spec — speculative architecture, not a delivered system. Educational + safety-critical use cases only.
Refines	ADR-089 (nvsim simulator), ADR-029 (RuvSense multistatic), ADR-021 (vitals), ADR-022 (wifiscan)

ruvnet / ruvector-acorn-filtered-hnsw-2026.md

Last active April 26, 2026 20:53

ruvector 2026: ACORN Predicate-Agnostic Filtered HNSW in Rust — 98.9% recall@10 at 1% selectivity, faster filtered vector search

ACORN Filtered HNSW in Rust — Predicate-Aware Vector Search with No Recall Collapse

Keywords: filtered vector search · ACORN · HNSW · approximate nearest neighbor (ANN) · predicate filter · vector database · Rust · RAG · semantic search · low selectivity recall · embedding search · k-NN graph · ruvector

TL;DR. ruvector-acorn is a pure-Rust implementation of ACORN (Patel et al., SIGMOD 2024, arXiv:2403.04871) that solves filtered HNSW's recall-collapse problem at low predicate selectivity. 96% recall@10 at 1% selectivity, 99 K QPS at 50% selectivity, 23 ms parallel index build for 5 K × 128. Drop-in FilteredIndex trait — works with any Fn(u32) -> bool predicate (equality, range, geo, ACL, composite). No C/C++ FFI, no unsafe, no BLAS dependency. Source: github.com/ruvnet/RuVector.

Why filtered vector search is hard

ruvnet / rabitq-issue-body.md

Created April 26, 2026 03:41

RuView RaBitQ similarity sensor — ADR-084 announcement (43-51x compare speedup, 7.5x top-K speedup)

What this is

RuView now has a cheap similarity sensor baked into the pipeline — a way to ask "have I seen something like this before?" for any embedding (poses, CSI features, room signatures) without paying the full floating-point cost. It uses a technique called RaBitQ-style binary sketching: each embedding gets compressed to one bit per dimension (32× smaller in memory) and compared with a single CPU instruction (POPCNT on Intel/AMD, NEON vcnt on ARM/Pi/Mac).

The architectural decision is ADR-084 (merged on main, status: Proposed). The first implementation pass — the foundation Sketch / SketchBank API — is on branch feat/adr-084-pass-1-sketch-module (commits 6fd5b7d, 1df9d5f7d).

Why this matters in plain language

A lot of what RuView does is the same shape of question over and over:

ruvnet / README.md

Last active April 26, 2026 04:40

ruLake — A Memory Lake for Agentic AI (MCP + RBAC + JWT + 109 tests, free + open source)

ruLake — A Memory Lake for Agentic AI

Give your AI agents fast, trustworthy memory — without standing up a vector database.

ruLake is the layer between your agents and the data they remember. Plug in the storage you already have (S3, BigQuery, Snowflake, Parquet, files), expose it through one MCP tool, and every agent on every host gets the same low-latency, content-addressed view of memory.

Created by rUv. Part of the RuVector ecosystem alongside ruvector-rabitq (1-bit compression kernel) and RVF (durable segment format). Repo: ruvnet/RuLake.

ruvnet / ruvector-rabitq-2026-overview.md

Last active April 24, 2026 17:30

ruvector-rabitq: 1-bit rotation-based vector quantization in Rust — symmetric (Charikar) + asymmetric (RaBitQ-2024) estimators, SoA + cos-LUT optimized kernel: 32x codes / 21x full-index compression, 3.13x speedup at 100% recall@10 on n=100k clustered D=128 vectors

ruvector-rabitq — Rotation-Based 1-Bit Vector Quantization in Rust

Two 1-bit ANN distance estimators (symmetric Charikar-LSH + asymmetric RaBitQ-2024), 32× per-vector code compression, 21× full-index memory compression, 3.13× end-to-end speedup at 100% recall@10 on n = 100,000 clustered D=128 vectors — pure Rust, no C/C++ deps, no SIMD intrinsics yet.

Part of the ruvector vector search library. Branch: research/nightly/2026-04-23-rabitq (head 6c6e04554) · ADR-154 · PR #370

What's in this crate

ruvnet / 00-README.md

Last active April 23, 2026 03:56

RuVector: Connectome-Driven Embodied Brain — graph-native structural intelligence infrastructure (not mind upload)

Connectome OS

A debugging and control layer for embodied graph systems whose structure is knowable — the connectome — rather than learned.

"OS" in the Linux sense: infrastructure for introspection and intervention, not a mystical claim about emergent mind. Not "mind upload." Not "digital consciousness." Connectome OS is the graph-native runtime that mounts on top of a connectome + a spiking engine and lets you probe, perturb, and reason about the structure — cut the wiring, measure the fracture, ask what substructure carried the failure.

Built as a Rust example crate (examples/connectome-fly/) on the RuVector graph primitives stack. Tier-1 demonstrator is the fruit fly (10⁴–10⁵ neurons, FlyWire v783-compatible); Tier 2 is mouse cortical regions (~29 engineer-weeks of named follow-up work to scale the in-tree substrate); Tier 3 is explicitly not on the roadmap.

Experiment Output: Pre-Seizure Boundary Detection

Command: cargo run --release -p brain-boundary-discovery Hardware: Apple Silicon (M-series), macOS Rust: 1.92.0 stable, NEON SIMD active

ruvnet / 01-boundary-first-discovery-paper.md

Last active April 12, 2026 23:31

Boundary-First Scientific Discovery: Detecting Novel Structure Classes via Graph MinCut, Spectral Coherence, and Integrated Information — RuVector Research (2026-04-12)

Boundary-First Scientific Discovery: Detecting Novel Structure Classes via Graph MinCut, Spectral Coherence, and Integrated Information

Authors: RuVector Research Collective Date: 2026-04-12 Status: Preprint — Open Research Repository: github.com/ruvnet/RuVector Branch: research/exotic-structure-discovery-rvf