vrr/ruvector
2
0
Fork 0
mirror of https://github.com/ruvnet/RuVector.git synced 2026-05-24 13:54:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 20
708 commits 176 branches 48 tags 582 MiB
Commit graph

708 commits

This branch
This branch
All branches
Author SHA1 Message Date
Reuven
d03e6d8ec5 docs(readme): add prime-radiant and ruvector-attention-wasm package references 
- Add prime-radiant to Quantum Coherence section (sheaf Laplacian AI safety)
- Add ruvector-attention-wasm to npm WASM packages (Flash, MoE, Hyperbolic, CGT)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 21:25:25 -05:00
Reuven
ab3a560bb2 fix(prime-radiant): shorten keyword for crates.io compliance 
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 21:24:02 -05:00
Reuven
374085c2e2 chore(prime-radiant): add version numbers to path dependencies for crates.io publish 2026-01-22 21:20:15 -05:00
Reuven
104e3e10bc chore(hyperbolic-hnsw): SEO optimize for crates.io publish 2026-01-22 21:19:23 -05:00
Reuven
e31422e920 chore: SEO optimize package metadata for crates.io and npm 
- prime-radiant: Enhanced description, keywords, categories
- ruvector-attention-wasm: Add version to path dep, SEO keywords
- package.json: 23 keywords, better description, engines config

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 20:20:50 -05:00
Reuven
cc7b4a9ccc perf(prime-radiant): add CSR sparse matrix, GPU buffer prealloc, thread-local scratch 
Performance optimizations for Prime-Radiant coherence engine:

CSR Sparse Matrix (restriction.rs):
- Full CsrMatrix struct with row_ptr, col_indices, values
- COO to CSR conversion with from_coo() and from_coo_arrays()
- Zero-allocation matvec_into() and matvec_add_into()
- SIMD-friendly 4-element loop unrolling
- 13 new tests covering all CSR operations

GPU Buffer Pre-allocation (engine.rs, kernels.rs):
- Pre-allocated params, energy_params, partial_sums, staging buffers
- Zero per-frame allocations in compute_energy()
- New create_bind_group_raw() methods for raw buffer references
- CSR matrix support in convert_restriction_map()

Thread-Local Scratch Buffers (edge.rs):
- EdgeScratch struct with 3 reusable Vec<f32> buffers
- thread_local! SCRATCH for zero-allocation hot paths
- residual_norm_squared_no_alloc() and weighted_residual_energy_no_alloc()
- 7 new tests for allocation-free energy computation

WGSL Vec4 Optimization (compute_residuals.wgsl):
- vec4-based processing loop with dot(r_vec, r_vec)
- store_residuals flag in GpuParams struct
- ~4x GPU throughput improvement

README Updates:
- Root README: 40 attention mechanisms, Prime-Radiant section, CGT Sheaf Attention
- WASM README: CGT Sheaf Attention API documentation

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 20:14:34 -05:00
Reuven
57109ed71b perf(prime-radiant): optimize SIMD and core computation patterns 
SIMD Optimizations:
- Replace element-by-element load_f32x8 with try_into for direct memory copy
- Fix redundant SIMD comparisons in lane assignment (compute masks once, use blend)
- Apply across vectors.rs, matrix.rs, and energy.rs

Core Computation Patterns:
- Replace i % 4 modulo with chunks_exact() for proper auto-vectorization
- Fix edge.rs: residual_norm_squared, residual_with_energy
- Fix node.rs: norm_squared, dot product

Graph API:
- Add get_node_ref() for zero-copy node access via DashMap reference
- Add with_node() closure API for efficient read-only operations

Benchmark findings:
- Incremental updates meet target (<100us): 59us actual
- Linear O(n) scaling confirmed
- Further SIMD/parallelization needed for <1us/edge target

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 20:02:11 -05:00
Reuven
231729fa5e feat(prime-radiant): add GPU acceleration, SIMD optimizations, and benchmarks 
GPU Acceleration (wgpu-rs):
- GpuCoherenceEngine with automatic CPU fallback
- GpuDevice: adapter/device management with high-perf selection
- GpuDispatcher: kernel execution with pipeline caching and buffer pooling
- GpuBufferManager: typed buffer management with pooling
- Compute kernels: residuals, energy reduction, sheaf attention, token routing

WGSL Compute Shaders (6 files, 1,412 lines):
- compute_residuals.wgsl: parallel edge residual computation
- compute_energy.wgsl: two-phase parallel reduction
- sheaf_attention.wgsl: energy-based attention weights A_ij = exp(-beta * E_ij)
- token_routing.wgsl: branchless lane assignment
- sparse_mask.wgsl: sparse attention mask generation
- types.wgsl: shared GPU struct definitions

SIMD Optimizations (wide crate):
- Runtime CPU feature detection (AVX2, AVX-512, SSE4.2, NEON)
- f32x8 vectorized operations
- simd/vectors.rs: dot_product_simd, norm_squared_simd, subtract_simd
- simd/matrix.rs: matmul_simd, matvec_simd, transpose_simd
- simd/energy.rs: batch_residuals_simd, weighted_energy_sum_simd
- 38 unit tests verifying SIMD correctness

Benchmarks (criterion):
- coherence_benchmarks.rs: core operations, graph scaling
- simd_benchmarks.rs: SIMD vs naive comparisons
- gpu_benchmarks.rs: CPU vs GPU performance

Tests:
- 18 GPU coherence tests (16 active, 2 perf ignored)
- GPU-CPU consistency within 1% relative error
- Error handling and fallback verification

README improvements:
- "What Prime-Radiant is NOT" section
- Concrete numeric example with arithmetic
- Flagship LLM hallucination refusal walkthrough
- Infrastructure positioning

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 16:59:25 -05:00
Reuven
f36334fc7a feat(prime-radiant): implement coherence engine with CGT attention 
Complete implementation of Prime-Radiant coherence engine and
Coherence-Gated Transformer (CGT) sheaf attention module.

Core Features:
- Sheaf Laplacian energy computation with restriction maps
- 4-lane compute ladder (Reflex/Retrieval/Heavy/Human)
- Cryptographic witness chains for audit trails
- Policy bundles with multi-party approval

Storage Backends:
- InMemoryStorage with KNN search
- FileStorage with Write-Ahead Logging (WAL)
- PostgresStorage with full schema (feature-gated)
- HybridStorage combining file + optional PostgreSQL

CGT Sheaf Attention (ruvector-attention):
- RestrictionMap with residual/energy computation
- SheafAttention layer: A_ij = exp(-β×E_ij)/Z
- TokenRouter with compute lane routing
- SparseResidualAttention with energy-based masking
- EarlyExit with energy convergence detection

Performance Optimizations:
- Zero-allocation hot paths (apply_into, compute_residual_norm_sq)
- SIMD-friendly 4-way unrolled loops
- Branchless lane routing
- Pre-allocated buffers for batch operations

RuvLLM Integration:
- SheafCoherenceValidator for LLM response validation
- UnifiedWitnessLog linking inference + coherence
- MemoryCoherenceLayer for contradiction detection
- CoherenceConfidence for interpretable uncertainty

Tests: 202 passing in ruvector-attention, 180+ in prime-radiant

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 16:00:53 -05:00
Reuven
c6219df04f docs(adr): add ADR-015 Coherence-Gated Transformer (Sheaf Attention) 
Propose novel low-latency transformer architecture using coherence energy:

Core Innovation:
- Route tokens to compute lanes based on coherence energy, not confidence
- Sparse attention using residual energy (skip coherent pairs)
- Early exit when energy converges (not confidence threshold)
- Restriction maps replace QKV projections

Architecture:
- Lane 0 (Reflex): 1-2 layers, local attention, <0.1ms
- Lane 1 (Standard): 6 layers, sparse sheaf attention, ~1ms
- Lane 2 (Deep): 12+ layers, full + MoE, ~5ms
- Lane 3 (Escalate): Return uncertainty

Performance Targets:
- 5-10x latency reduction (10ms → 1-2ms for 128 tokens)
- 2.5x memory reduction
- <5% quality degradation
- Provable coherence bound on output

Mathematical Foundation:
- Attention weight ∝ exp(-β × residual_energy)
- Token routing via E(t) = Σ w_e ||ρ_t(x) - ρ_ctx(x)||²
- Early exit when ΔE < ε (energy converged)

Target: ruvector-attention crate with sheaf/ and coherence_gated/ modules

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 13:29:41 -05:00
Reuven
3d70c36d75 docs(prime-radiant): add comprehensive README with examples 
Add user-friendly documentation covering:
- Introduction explaining coherence vs confidence
- Core concepts (coherence field, compute ladder)
- Features overview (engine, governance, RuvLLM integration)
- Quick start code examples:
  - Basic coherence check
  - LLM response validation
  - Memory consistency tracking
  - Confidence from energy
- Application tiers (today, near-term, future)
- Domain examples (AI, finance, medical, robotics, security)
- Feature flags reference
- Performance targets
- Architecture diagram

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 13:16:49 -05:00
Reuven
c5fe7f93d6 feat(prime-radiant): implement RuvLLM integration layer (ADR-014 v0.4) 
Implement complete Prime-Radiant + RuvLLM integration per ADR-CE-016 through ADR-CE-022:

Core Integration Modules:
- coherence_validator.rs: SheafCoherenceValidator using sheaf energy
- witness_log.rs: UnifiedWitnessLog with hash chain for tamper evidence
- pattern_bridge.rs: PatternToRestrictionBridge learning from verdicts
- memory_layer.rs: MemoryCoherenceLayer tracking context as sheaf nodes
- confidence.rs: CoherenceConfidence with sigmoid energy→confidence mapping

Supporting Infrastructure:
- mod.rs: Public API, re-exports, convenience constructors
- error.rs: Comprehensive error types for each ADR
- config.rs: LlmCoherenceConfig, thresholds, policies
- gate.rs: LlmCoherenceGate high-level interface
- adapter.rs: RuvLlmAdapter bridging type systems
- bridge.rs: PolicyBridge, SonaBridge for synchronization
- witness.rs: WitnessAdapter for correlation
- traits.rs: Trait definitions for loose coupling

Testing:
- 22 integration tests covering all modules
- Self-contained mock implementations
- Feature-gated with #[cfg(feature = "ruvllm")]

Feature Flags:
- ruvllm feature in Cargo.toml
- Optional dependency on ruvllm crate
- Added to "full" feature set

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 13:04:30 -05:00
Reuven
2a4aa1fb35 docs(adr): add 22 coherence engine internal ADRs 
Create detailed ADR files for all internal coherence engine decisions:

Core Architecture (ADR-CE-001 to ADR-CE-008):
- 001: Sheaf Laplacian defines coherence witness
- 002: Incremental computation with stored residuals
- 003: PostgreSQL + ruvector hybrid storage
- 004: Signed event log with deterministic replay
- 005: First-class governance objects
- 006: Coherence gate controls compute ladder
- 007: Thresholds auto-tuned from traces
- 008: Multi-tenant isolation boundaries

Universal Coherence (ADR-CE-009 to ADR-CE-015):
- 009: Single coherence object (one math, many interpretations)
- 010: Domain-agnostic nodes and edges
- 011: Residual = contradiction energy
- 012: Gate = refusal mechanism with witness
- 013: Not prediction (coherence field, not forecasting)
- 014: Reflex lane default (most ops stay fast)
- 015: Adapt without losing control

RuvLLM Integration (ADR-CE-016 to ADR-CE-022):
- 016: CoherenceValidator uses sheaf energy
- 017: Unified audit trail (WitnessLog + governance)
- 018: Pattern-to-restriction bridge (ReasoningBank)
- 019: Memory as nodes (agentic, working, episodic)
- 020: Confidence from energy (sigmoid mapping)
- 021: Shared SONA between ruvllm and prime-radiant
- 022: Failure learning (ErrorPatternLearner → ρ maps)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 12:53:44 -05:00
Reuven
cc5f073b74 docs(adr): add RuvLLM integration to ADR-014 v0.4 
- Add coherence-gated LLM inference architecture diagram
- Add 5 integration modules with code examples:
  - SheafCoherenceValidator (replaces heuristic scoring)
  - UnifiedWitnessLog (merged audit trail)
  - PatternToRestrictionBridge (ReasoningBank → learned ρ)
  - MemoryCoherenceLayer (context as sheaf nodes)
  - CoherenceConfidence (energy → confidence mapping)
- Add 7 integration ADRs (ADR-CE-016 through ADR-CE-022)
- Add ruvllm to crate integration matrix and dependencies
- Add 4 LLM-specific benefits to consequences
- Add ruvllm feature flag

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 12:44:17 -05:00
Reuven
1122e9409a feat(prime-radiant): implement sheaf Laplacian coherence engine 
Implement the complete Prime-Radiant crate based on ADR-014:

Core Modules:
- substrate/: SheafGraph, SheafNode, SheafEdge, RestrictionMap (SIMD-optimized)
- coherence/: CoherenceEngine, energy computation, spectral drift detection
- governance/: PolicyBundle, WitnessRecord, LineageRecord (Blake3 hashing)
- execution/: CoherenceGate, ComputeLane, ActionExecutor

Ecosystem Integrations (feature-gated):
- tiles/: cognitum-gate-kernel 256-tile WASM fabric adapter
- sona_tuning/: Adaptive threshold learning with EWC++
- neural_gate/: Biologically-inspired gating with HDC encoding
- learned_rho/: GNN-based learned restriction maps
- attention/: Topology-gated attention, MoE routing, PDE diffusion
- distributed/: Raft-based multi-node coherence

Testing:
- 138 tests (integration, property-based, chaos)
- 8 benchmarks covering ADR-014 performance targets

Stats: 91 files, ~30K lines of Rust code

"This is not prediction. It is a continuously updated field of coherence
that shows where action is safe and where action must stop."

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 12:36:42 -05:00
Reuven
4709ff8c92 docs(coherence-engine): add ADR-014 and DDD for sheaf Laplacian coherence engine 
Add comprehensive architecture documentation for ruvector-coherence crate:

- ADR-014: Sheaf Laplacian-based coherence witnessing architecture
  - Universal coherence object with domain-agnostic interpretation
  - 5-layer architecture (Application → Gate → Computation → Governance → Storage)
  - 4-tier compute ladder (Reflex → Retrieval → Heavy → Human)
  - Full ruvector ecosystem integration (10+ crates)
  - 15 internal architectural decisions

- DDD: Domain-Driven Design with 10 bounded contexts
  - Tile Fabric (cognitum-gate-kernel)
  - Adaptive Learning (sona)
  - Neural Gating (ruvector-nervous-system)
  - Learned Restriction Maps (ruvector-gnn)
  - Hyperbolic Coherence (ruvector-hyperbolic-hnsw)
  - Incoherence Isolation (ruvector-mincut)
  - Attention-Weighted Coherence (ruvector-attention)
  - Distributed Consensus (ruvector-raft)

Key concept: "This is not prediction. It is a continuously updated field
of coherence that shows where action is safe and where action must stop."

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 11:24:04 -05:00
Reuven
92a88a86ff docs(readme): add Cognitum Gate and Neuromorphic Discoveries to Use Cases 
## AI Safety & Coherence (Cognitum Gate)
- 256-tile WASM fabric for real-time safety decisions
- TileZero arbiter with supergraph merging
- Permit/Defer/Deny decisions with cryptographic tokens
- Hash-chained witness receipts for audit trails
- Anytime-valid sequential hypothesis testing
- Rust and JavaScript code examples

## Neuromorphic Computing (micro-hnsw v2.3)
- Spike-Timing Vector Encoding for temporal similarity
- Homeostatic Plasticity for self-stabilizing networks
- Oscillatory Resonance (40Hz gamma) for search amplification
- Winner-Take-All circuits with lateral inhibition
- Dendritic Computation for non-linear local processing
- STDP learning integration
- 11.8KB WASM footprint for edge/embedded

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:57:36 -05:00
Reuven
ccf5983db9 docs(readme): add Dynamic Embedding Fine-Tuning to RuvLLM section 
- MicroLoRA per-request adaptation (<1ms, <50KB adapters)
- Contrastive training with triplet loss and hard negatives
- Task-specific adapters: Coder, Researcher, Security, Architect, Reviewer
- EWC++ for catastrophic forgetting prevention
- Adapter merging strategies: Average, Weighted, SLERP, TIES, DARE
- JavaScript and Rust code examples for fine-tuning
- Links to Fine-Tuning Guide and Task Adapters docs

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:55:19 -05:00
Reuven
e481755ed1 docs(readme): add Dynamic Embedding Fine-Tuning to Use Cases 
- Real-time MicroLoRA adaptation (<1ms per request)
- Contrastive training with triplet loss and hard negatives
- Task-specific adapters (Coder, Researcher, Security, Architect, Reviewer)
- EWC++ for catastrophic forgetting prevention
- Browser fine-tuning with MicroLoRA WASM (<50KB adapters)
- Three-tier adaptation system: Instant, Background, Deep
- Code examples for JavaScript, Rust, and browser WASM

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:54:30 -05:00
Reuven
7bdd3f208a docs(readme): expand Use Cases section with 8 categories and examples 
- AI & LLM Applications: RAG, agent routing, multi-agent orchestration
- Search & Discovery: semantic, hybrid, image similarity, code search
- Recommendations & Personalization: products, content, similar items
- Knowledge Management: knowledge graphs, document Q&A, scientific papers
- Real-Time & Edge: browser AI, IoT, mobile, streaming
- Scientific & Research: neural networks, trading, quantum, brain connectivity
- Distributed & Enterprise: multi-region, HA, PostgreSQL, burst scaling
- Agentic Workflows: version control, DAG pipelines, web scraping

Each category includes feature tables, code examples, and links to examples/

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:52:10 -05:00
Reuven
bf95df5000 docs(readme): complete Rust Crates section with all 63 packages 
- Add missing crates: micro-hnsw-wasm, ruvector-postgres, rvlite, sona
- Add new sections: Self-Learning (SONA), Standalone Edge Database (rvLite), PostgreSQL Extension
- Remove non-existent profiling crate reference
- All 63 crates in crates/ directory now documented

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:49:53 -05:00
Reuven
3699ab9976 docs(readme): expand npm packages section with all 45+ packages 
Reorganized npm packages into categories:
- Core Packages (4): ruvector, core, node, extensions
- Graph & GNN (4): gnn, graph-node, graph-wasm, graph-data-generator
- AI Routing & Attention (3): tiny-dancer, router, attention
- Learning & Neural (2): sona, spiking-neural
- LLM Runtime (3): ruvllm, ruvllm-cli, ruvllm-wasm
- Distributed Systems (5): cluster, server, raft, replication, burst-scaling
- Edge & Standalone (2): rvlite, rudag
- Agentic & Synthetic Data (3): agentic-synth, agentic-integration, cognitum/gate
- CLI Tools (3): cli, postgres-cli, scipix
- WASM Packages (10): wasm, wasm-unified, gnn-wasm, attention-wasm, etc.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:44:36 -05:00
Reuven
02c7db9f70 docs(readme): organize sections into logical groups 
Added section group headers to improve navigation:
- Package Reference (Documentation, npm, Rust crates)
- Platform Features (DAG, rvLite, Edge-Net)
- AI & Machine Learning (Synth, Neural Trader, RuvLLM, SNN, REFRAG, etc.)
- Database Extensions (PostgreSQL)
- Developer Tools (Utilities)
- Browser & Edge (WASM packages)
- Self-Learning Systems (Intelligence Hooks)
- Additional Modules (OCR, ONNX, Bindings)
- Examples & Tutorials
- Project (Structure)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:40:58 -05:00
Reuven
ab56289d0b docs(readme): add 7 comprehensive example sections 
Added collapsed sections with badges, feature tables, and tutorials for:
- Agentic-Jujutsu: Quantum-resistant version control (23x faster commits)
- SciPix: Scientific document OCR (50ms text, 80ms math)
- Meta-Cognition SNN: Spiking neural networks (5-54x SIMD speedup)
- RuvLLM: Self-learning LLM orchestration (SONA 3-tier learning)
- REFRAG: Compress-Sense-Expand RAG (~30x latency reduction)
- 7sense: Bioacoustic bird call analysis (150x HNSW speedup)
- EXO-AI: Cognitive substrate with IIT consciousness (8-54x SIMD)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:38:49 -05:00
Reuven
10ebf2beb5 docs(readme): add Neural Trader AI trading system section 
- 4 core AI/ML engines: Kelly, LSTM-Transformer, DRL Portfolio, Sentiment
- Research-backed algorithms table
- Quick start with code examples
- Use cases: stocks, sports betting, crypto, news trading
- 20+ package ecosystem table
- CLI interface examples
- Exotic examples: swarm, GNN, quantum, hyperbolic
- Performance benchmarks table

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:33:12 -05:00
Reuven
cdca236b2f docs(readme): add downloads badge for rvLite, add Agentic-Synth section 
rvLite:
- Add downloads badge linking to npm package

Agentic-Synth - AI Synthetic Data Generation:
- Problem/Solution comparison table
- Key features: multi-model, caching, routing, DSPy.ts
- Data generation types: time-series, events, structured, embeddings
- Quick start with npx commands
- Basic usage examples (structured, time-series, streaming)
- Self-learning with DSPy optimizer example
- Performance metrics (98.2% faster with caching)
- Ecosystem integration table

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:31:42 -05:00
Reuven
4c44894c8a docs(readme): add rvLite and Edge-Net collapsed sections 
rvLite - Standalone Edge Database:
- Architecture diagram showing WASM crate composition
- SQL, SPARQL, Cypher query examples
- GNN embeddings and ReasoningBank learning
- Platform support table (browsers, Node, Deno, Bun, Workers)
- Size budget breakdown (~2.3MB total)

Edge-Net - Collective AI Computing Network:
- Network architecture diagram
- How it works: contribute, earn, use cycle
- AI Intelligence Stack (MicroLoRA, SONA, HNSW, Federated Learning)
- Pi-Key identity system (π, e, φ keys)
- Quick start: join collective, submit tasks, monitor stats
- Self-optimizing features (routing, topology, Q-learning security)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:30:42 -05:00
Reuven
be248d5f48 docs(readme): add comprehensive Self-Learning DAG section 
New collapsed section includes:
- Introduction and key benefits (50-80% latency reduction)
- Use cases (vector search, APIs, analytics, edge, multi-tenant)
- How it works diagram with MinCut tension explanation
- 7 DAG attention mechanisms table
- Quick start for Rust, Node.js, and Browser (WASM)
- SONA learning integration example
- Self-healing (reactive + predictive) code
- Query convergence demonstration
- Performance targets table
- Installation instructions

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:28:17 -05:00
Reuven
38fe7762dd docs(readme): expand Core Features and Comparison tables 
Core Features & Capabilities:
- Add LLM Runtime section (ruvllm, WebGPU, RuvLTRA, quantization)
- Add Platform & Edge section (rvLite, PostgreSQL, MCP, WASM, Node.js)
- Add Specialized Processing (SciPix, DAG, Cognitum, FPGA, ruQu, Mincut)
- Add Self-Learning & Adaptation (hooks, ReasoningBank, Economy, Nervous)
- Expand existing sections with Hyperbolic HNSW, Sparse Vectors, Local Embeddings

Comparison Table:
- Add DAG Workflows, ReasoningBank, Economy System, Nervous System
- Add Cognitum Gate, SciPix OCR, Spiking Neural Nets
- Add Node.js Native, Burst Scaling, Streaming API
- Fix Local Embeddings count (6 → 8+)
- Add WebGPU to Browser/WASM

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:26:23 -05:00
Reuven
fb5648e399 fix(ruvllm-wasm): reduce keywords to 5 for crates.io compliance 
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:23:45 -05:00
Reuven
0a46a8b6c0 docs: add ruvllm-wasm README and improve Bindings & Tools section 
- Add comprehensive README.md for ruvllm-wasm crate
- Improve Bindings & Tools section with intro and usage examples
- Add Node.js, Browser, CLI, and HTTP Server examples

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:20:50 -05:00
Reuven
62f7e15dc8 docs: improve PostgreSQL section with better intro and Docker Hub info 
- Add better intro explaining why RuVector Postgres
- Update Docker Hub URL to ruvnet/ruvector-postgres
- Add environment variables table
- Update Docker Compose with correct image
- Add quick install command at top

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:18:42 -05:00
Reuven
3c63a75c06 docs: make Tools & Utilities section collapsible 
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:17:36 -05:00
Reuven
e9a613a256 docs: fix PostgreSQL section nesting - now top-level collapsible 
- Close Rust Crates section before PostgreSQL
- Remove extra </details> tag

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:16:20 -05:00
Reuven
d13cee0612 docs: make PostgreSQL Extension section collapsible 
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:14:39 -05:00
Reuven
81fd22c49e docs: add rvlite to WASM & Utility Packages section 
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:13:36 -05:00
Reuven
e16773b473 docs: add comprehensive PostgreSQL section with Docker/npm/crate instructions 
- Add feature comparison table (pgvector vs RuVector Postgres)
- Docker: quick start, docker-compose, available tags
- npm CLI: commands, programmatic TypeScript usage
- Rust crate: cargo-pgrx installation, features
- SQL examples: HNSW, hybrid search, GNN, local embeddings

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:12:52 -05:00
Reuven
a0d7a800a5 docs: expand capabilities section from 14 to 30+ features 
Organized into categories:
- Core Vector Database (5)
- Distributed Systems (4)
- AI & Machine Learning (7)
- Specialized Processing (5)
- Platform & Integration (4)
- Self-Learning & Adaptation (5)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:10:11 -05:00
Reuven
a540d9cfdd docs: minor README formatting fixes 
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:07:54 -05:00
Reuven
b35bfce6a2 feat(npm): add @ruvector/ruvllm-cli and @ruvector/ruvllm-wasm packages 
- Add @ruvector/ruvllm-cli v0.1.0: CLI for LLM inference with Metal/CUDA
- Add @ruvector/ruvllm-wasm v0.1.0: Browser LLM inference with WebGPU
- Remove duplicate npm/packages/wasm (replaced by ruvector-wasm)
- Fix workspace:* reference in ruvector-wasm-unified
- Update README with npm packages section

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-22 00:06:03 -05:00
Reuven
8f5b2bdb03 docs: add new npm packages to README 
- Move @ruvector/raft, @ruvector/replication, @ruvector/scipix from
  Planned to Published section with badges and download counts
- Add new "Distributed Systems (Raft & Replication)" section with:
  - Crate table with badges
  - Feature highlights (consensus, vector clocks, conflict resolution)
  - TypeScript code example for both packages
  - Links to package documentation
- Expand SciPix section with:
  - npm package reference alongside Rust crate
  - Feature list (multi-format, batch, content detection, PDF)
  - TypeScript client code example
  - Link to npm package README
- Update package count from 40+ to 45+

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-21 23:57:03 -05:00
Reuven
860549f100 docs: add total downloads badge to README 
Add npm total downloads badge alongside monthly downloads.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-21 23:52:16 -05:00
rUv
5a7637035d
chore: move packages to npm/packages directory (#130) 
Consolidate all npm packages under npm/packages/:
- cognitum-gate-wasm
- ruvector-wasm-unified
- ruvector-wasm

Co-authored-by: Reuven <cohen@ruv-mac-mini.local>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-21 23:50:45 -05:00
Reuven
2db4805fd7 chore: reorganize scripts into subfolders 
Create organized structure:
- benchmark/ - Performance benchmarking scripts
- ci/ - CI/CD automation scripts
- deploy/ - Deployment scripts and docs
- publish/ - Package publishing scripts
- test/ - Testing scripts
- validate/ - Validation & verification scripts

Update README with new structure and usage examples.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-21 23:48:37 -05:00
Reuven
3e5a4e3e83 chore: remove logs directory 
Logs should not be tracked in version control.
Already in .gitignore.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-21 23:45:34 -05:00
Reuven
8b99c98a83 docs: update .env.example with comprehensive config 
Add environment variables for:
- NPM publishing token
- AI provider API keys (Anthropic, OpenAI, Google)
- HuggingFace configuration
- Claude Flow configuration
- Database connections
- Cloud deployment
- Monitoring & observability

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-21 23:44:53 -05:00
Reuven
c06eb269aa docs: reorganize into subfolders 
- Create new directories: security/, code-reviews/, analysis/
- Move benchmark files to benchmarks/
- Move security audit files to security/
- Move analysis/research files to analysis/
- Move code review files to code-reviews/
- Move implementation files to implementation/
- Move integration files to integration/
- Move training/LoRA files to training/
- Move architecture files to architecture/
- Move optimization guides to optimization/
- Update INDEX.md with new structure
- Update README.md with new structure
- Update REPO_STRUCTURE.md with new structure

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-21 23:43:50 -05:00
Reuven
9642bb04f4 chore: add .DS_Store to gitignore 
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-21 23:40:07 -05:00
Reuven
34b6f1cff6 chore: remove .DS_Store files 
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-21 23:39:49 -05:00
Reuven
4259651601 chore: clean up root directory files 
Remove working files that were incorrectly saved to root folder.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-21 23:39:21 -05:00