vrr/ruvector
2
0
Fork 0
mirror of https://github.com/ruvnet/RuVector.git synced 2026-06-02 07:29:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2
2409 commits 187 branches 49 tags 603 MiB
Commit graph

2409 commits

This branch
This branch
All branches
Author SHA1 Message Date
rUv
6a47e37264 feat(edge): add WASM bindings and publish @ruvector/edge v0.1.1 
WASM Implementation:
- Add wasm.rs with bindings for all core P2P types
- Configure Cargo.toml with wasm/native feature flags
- Gate native-only modules (tokio, transport) behind feature flags
- Convert intelligence.rs and memory.rs to sync (parking_lot::RwLock)
- Fix distributed_learning.rs example for sync API

Exports:
- WasmIdentity, WasmCrypto, WasmHnswIndex
- WasmSemanticMatcher, WasmRaftNode, WasmHybridKeyPair
- WasmSpikingNetwork, WasmQuantizer, WasmAdaptiveCompressor

Build:
- WASM: wasm-pack build --no-default-features --features wasm
- Native: cargo build --features native
- Tests: 60 passing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 20:16:15 +00:00
rUv
89f3794402 feat(edge): add WASM bindings and publish @ruvector/edge v0.1.1 
WASM Implementation:
- Add wasm.rs with bindings for all core P2P types
- Configure Cargo.toml with wasm/native feature flags
- Gate native-only modules (tokio, transport) behind feature flags
- Convert intelligence.rs and memory.rs to sync (parking_lot::RwLock)
- Fix distributed_learning.rs example for sync API

Exports:
- WasmIdentity, WasmCrypto, WasmHnswIndex
- WasmSemanticMatcher, WasmRaftNode, WasmHybridKeyPair
- WasmSpikingNetwork, WasmQuantizer, WasmAdaptiveCompressor

Build:
- WASM: wasm-pack build --no-default-features --features wasm
- Native: cargo build --features native
- Tests: 60 passing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 20:16:15 +00:00
rUv
72619d1f9c docs(edge): improve README with free edge swarm introduction 
- Emphasize zero-cost edge-first architecture
- Add economics comparison (cloud vs edge)
- Document all WASM APIs with examples
- Add use cases and architecture diagram
- Compare with cloud alternatives (OpenAI, LangChain, AutoGPT)
- Include agentic-flow integration example

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 20:15:24 +00:00
rUv
4e0be8eb61 docs(edge): improve README with free edge swarm introduction 
- Emphasize zero-cost edge-first architecture
- Add economics comparison (cloud vs edge)
- Document all WASM APIs with examples
- Add use cases and architecture diagram
- Compare with cloud alternatives (OpenAI, LangChain, AutoGPT)
- Include agentic-flow integration example

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 20:15:24 +00:00
rUv
da0bf30c93 feat(edge): add WASM npm package @ruvector/edge 
- Built WASM bindings with wasm-pack for browser/Node.js usage
- Exports: WasmIdentity, WasmCrypto, WasmHnswIndex, WasmSemanticMatcher,
  WasmRaftNode, WasmHybridKeyPair, WasmSpikingNetwork, WasmQuantizer,
  WasmAdaptiveCompressor
- 364KB optimized WASM binary with full TypeScript types
- Published to npm as @ruvector/edge@0.1.0

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 20:11:26 +00:00
rUv
642645e6ad feat(edge): add WASM npm package @ruvector/edge 
- Built WASM bindings with wasm-pack for browser/Node.js usage
- Exports: WasmIdentity, WasmCrypto, WasmHnswIndex, WasmSemanticMatcher,
  WasmRaftNode, WasmHybridKeyPair, WasmSpikingNetwork, WasmQuantizer,
  WasmAdaptiveCompressor
- 364KB optimized WASM binary with full TypeScript types
- Published to npm as @ruvector/edge@0.1.0

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 20:11:26 +00:00
rUv
d35b827471 docs(edge): comprehensive README overhaul 
- Added badges (Rust, License, Tests, Security, WASM)
- New "Why RuVector Edge?" section explaining problem/solution
- Key Benefits table with quantified impacts
- Unique Capabilities table with 8 advanced features
- Features organized by category (Security, Intelligence, Performance, Distributed)
- Updated architecture diagram with Advanced Intelligence layer
- 7 comprehensive usage examples:
  - HNSW Vector Search
  - Post-Quantum Signatures
  - Spiking Neural Networks
  - Raft Consensus
  - Semantic Task Matching
  - Adaptive Compression
- Performance benchmarks table
- Zero-Trust Identity Chain documentation
- Comparison table vs libp2p, Matrix, NATS
- API Reference with Core Types table
- Complete exports listing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 18:48:00 +00:00
rUv
1ada4eeae8 docs(edge): comprehensive README overhaul 
- Added badges (Rust, License, Tests, Security, WASM)
- New "Why RuVector Edge?" section explaining problem/solution
- Key Benefits table with quantified impacts
- Unique Capabilities table with 8 advanced features
- Features organized by category (Security, Intelligence, Performance, Distributed)
- Updated architecture diagram with Advanced Intelligence layer
- 7 comprehensive usage examples:
  - HNSW Vector Search
  - Post-Quantum Signatures
  - Spiking Neural Networks
  - Raft Consensus
  - Semantic Task Matching
  - Adaptive Compression
- Performance benchmarks table
- Zero-Trust Identity Chain documentation
- Comparison table vs libp2p, Matrix, NATS
- API Reference with Core Types table
- Complete exports listing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 18:48:00 +00:00
rUv
74484eee38 feat(edge/p2p): complete RuVector advanced integrations 
Added:
- Semantic embeddings interface with hash-based LSH encoding
- SemanticTaskMatcher for intelligent agent-task matching
- Raft consensus protocol for distributed task coordination
  - Leader election with term-based voting
  - Log replication with consistency checks
  - Heartbeat and append entries protocol

Now exports 20+ advanced types from p2p module:
- Quantization: ScalarQuantized, BinaryQuantized, CompressedData
- HDC: Hypervector, HdcMemory, HDC_DIMENSION
- Compression: AdaptiveCompressor, NetworkCondition
- Pattern routing: PatternRouter
- Vector index: HnswIndex
- Post-quantum: HybridKeyPair, HybridPublicKey, HybridSignature
- Spiking networks: LIFNeuron, SpikingNetwork
- Embeddings: SemanticEmbedder, SemanticTaskMatcher
- Consensus: RaftNode, RaftState, LogEntry, RaftVoteRequest/Response, RaftAppendEntries/Response

60 tests passing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 18:37:57 +00:00
rUv
50549fc2c2 feat(edge/p2p): complete RuVector advanced integrations 
Added:
- Semantic embeddings interface with hash-based LSH encoding
- SemanticTaskMatcher for intelligent agent-task matching
- Raft consensus protocol for distributed task coordination
  - Leader election with term-based voting
  - Log replication with consistency checks
  - Heartbeat and append entries protocol

Now exports 20+ advanced types from p2p module:
- Quantization: ScalarQuantized, BinaryQuantized, CompressedData
- HDC: Hypervector, HdcMemory, HDC_DIMENSION
- Compression: AdaptiveCompressor, NetworkCondition
- Pattern routing: PatternRouter
- Vector index: HnswIndex
- Post-quantum: HybridKeyPair, HybridPublicKey, HybridSignature
- Spiking networks: LIFNeuron, SpikingNetwork
- Embeddings: SemanticEmbedder, SemanticTaskMatcher
- Consensus: RaftNode, RaftState, LogEntry, RaftVoteRequest/Response, RaftAppendEntries/Response

60 tests passing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 18:37:57 +00:00
rUv
c85598a978 feat(edge/p2p): add advanced RuVector integrations 
- HNSW vector indexing for O(log n) nearest neighbor search
- Hybrid post-quantum signatures (Ed25519 + Dilithium-style)
- Spiking neural networks (LIF neurons with STDP learning)
- Binary/Scalar quantization (4-32x compression)
- Hyperdimensional Computing for pattern matching
- Adaptive compression based on network conditions
- HDC-based semantic task routing

54 tests passing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 18:35:37 +00:00
rUv
8a93b410df feat(edge/p2p): add advanced RuVector integrations 
- HNSW vector indexing for O(log n) nearest neighbor search
- Hybrid post-quantum signatures (Ed25519 + Dilithium-style)
- Spiking neural networks (LIF neurons with STDP learning)
- Binary/Scalar quantization (4-32x compression)
- Hyperdimensional Computing for pattern matching
- Adaptive compression based on network conditions
- HDC-based semantic task routing

54 tests passing

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 18:35:37 +00:00
rUv
85a5ec7e68 docs(edge): Update README with P2P Swarm security documentation 
- Add P2P Swarm Layer to architecture diagram
- Document Ed25519/X25519 crypto and AES-256-GCM encryption
- Add security features table and code examples
- Document task execution with signed receipts
- Add GUN integration section
- Include P2P Security Model and Identity Trust Chain
- Add Key Derivation formula
- Update performance metrics with crypto ops/sec
- Add feature flags documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 18:06:56 +00:00
rUv
d59212910f docs(edge): Update README with P2P Swarm security documentation 
- Add P2P Swarm Layer to architecture diagram
- Document Ed25519/X25519 crypto and AES-256-GCM encryption
- Add security features table and code examples
- Document task execution with signed receipts
- Add GUN integration section
- Include P2P Security Model and Identity Trust Chain
- Add Key Derivation formula
- Update performance metrics with crypto ops/sec
- Add feature flags documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 18:06:56 +00:00
Claude
d7cc7ea32c docs(neural-trader): comprehensive README with features, benchmarks, use cases 
- Add introduction and core engine documentation
- Document all 4 production modules with code examples
- Add benefits section highlighting zero dependencies, research basis
- Include 5 use cases: stocks, sports betting, crypto, news, rebalancing
- Add detailed benchmark tables showing sub-millisecond performance
- Include comparative analysis vs TensorFlow.js, Brain.js, Synaptic
 2025-12-31 18:03:56 +00:00
Claude
908596bf39 docs(neural-trader): comprehensive README with features, benchmarks, use cases 
- Add introduction and core engine documentation
- Document all 4 production modules with code examples
- Add benefits section highlighting zero dependencies, research basis
- Include 5 use cases: stocks, sports betting, crypto, news, rebalancing
- Add detailed benchmark tables showing sub-millisecond performance
- Include comparative analysis vs TensorFlow.js, Brain.js, Synaptic
 2025-12-31 18:03:56 +00:00
rUv
5293e47370 feat(edge): Production-grade P2P Swarm with Ed25519/X25519 crypto 
Implements a production-grade P2P swarm coordination layer with:

Security Features:
- Ed25519 identity keys + X25519 ephemeral keys for ECDH
- AES-256-GCM authenticated encryption
- Canonical JSON serialization (sorted keys) for signatures
- Registry-based identity binding (never trust envelope keys)
- Message replay protection (nonces, counters, timestamps)
- Signed task receipts with full execution binding

Core Modules:
- identity.rs: Ed25519/X25519 key management, member registry
- crypto.rs: AES-256-GCM, canonical JSON, hashing
- envelope.rs: SignedEnvelope, TaskEnvelope, TaskReceipt types
- relay.rs: GUN relay health monitoring and failover
- artifact.rs: Local CID-based storage with LRU eviction
- swarm.rs: P2PSwarmV2 coordinator with heartbeats and task claiming

Additional:
- gun.rs: GUN decentralized database integration for swarm sync
- Examples: local_swarm.rs, distributed_learning.rs

All tests pass. Demo runs successfully.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 18:03:34 +00:00
rUv
764cb91585 feat(edge): Production-grade P2P Swarm with Ed25519/X25519 crypto 
Implements a production-grade P2P swarm coordination layer with:

Security Features:
- Ed25519 identity keys + X25519 ephemeral keys for ECDH
- AES-256-GCM authenticated encryption
- Canonical JSON serialization (sorted keys) for signatures
- Registry-based identity binding (never trust envelope keys)
- Message replay protection (nonces, counters, timestamps)
- Signed task receipts with full execution binding

Core Modules:
- identity.rs: Ed25519/X25519 key management, member registry
- crypto.rs: AES-256-GCM, canonical JSON, hashing
- envelope.rs: SignedEnvelope, TaskEnvelope, TaskReceipt types
- relay.rs: GUN relay health monitoring and failover
- artifact.rs: Local CID-based storage with LRU eviction
- swarm.rs: P2PSwarmV2 coordinator with heartbeats and task claiming

Additional:
- gun.rs: GUN decentralized database integration for swarm sync
- Examples: local_swarm.rs, distributed_learning.rs

All tests pass. Demo runs successfully.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 18:03:34 +00:00
Claude
763e190dee feat(neural-trader): add CLI, visualization, tests, and strategies 
- Add CLI tool with run, backtest, paper trading, analyze, and benchmark
- Add visualization module with ASCII charts (line, bar, sparkline, table)
- Create Jest test suite covering all production modules
- Implement example strategies: Hybrid Momentum, Mean Reversion, Sentiment

Performance benchmarks show all modules production-ready:
- Kelly Engine: 0.014ms (71,294/s)
- LSTM-Transformer: 0.681ms (1,468/s)
- DRL Portfolio: 0.059ms (17,043/s)
- Sentiment Alpha: 0.266ms (3,764/s)
 2025-12-31 17:51:23 +00:00
Claude
d0113aff45 feat(neural-trader): add CLI, visualization, tests, and strategies 
- Add CLI tool with run, backtest, paper trading, analyze, and benchmark
- Add visualization module with ASCII charts (line, bar, sparkline, table)
- Create Jest test suite covering all production modules
- Implement example strategies: Hybrid Momentum, Mean Reversion, Sentiment

Performance benchmarks show all modules production-ready:
- Kelly Engine: 0.014ms (71,294/s)
- LSTM-Transformer: 0.681ms (1,468/s)
- DRL Portfolio: 0.059ms (17,043/s)
- Sentiment Alpha: 0.266ms (3,764/s)
 2025-12-31 17:51:23 +00:00
rUv
ae32e23d5b chore: update intelligence data and version bump to v0.1.71 2025-12-31 17:40:37 +00:00
rUv
0f8f42e25b chore: update intelligence data and version bump to v0.1.71 2025-12-31 17:40:37 +00:00
rUv
4f4e80381d feat(edge): add ruv-swarm-transport integration example 
New example: examples/edge/
- Distributed AI swarm communication using ruv-swarm-transport
- WebSocket, SharedMemory, and WASM transport support
- Intelligence sync for distributed Q-learning patterns
- Shared vector memory for collaborative RAG
- LZ4 + quantization tensor compression (up to 12x)
- Protocol with Join, Sync, Task, Election messages
- Agent roles: Coordinator, Worker, Scout, Specialist

Binaries:
- edge-demo: Demo of distributed learning
- edge-agent: CLI agent that joins swarm
- edge-coordinator: Swarm coordinator

Dependencies:
- ruv-swarm-transport v1.0.5
- tokio, serde, lz4_flex, clap
 2025-12-31 17:20:51 +00:00
rUv
0368f883df feat(edge): add ruv-swarm-transport integration example 
New example: examples/edge/
- Distributed AI swarm communication using ruv-swarm-transport
- WebSocket, SharedMemory, and WASM transport support
- Intelligence sync for distributed Q-learning patterns
- Shared vector memory for collaborative RAG
- LZ4 + quantization tensor compression (up to 12x)
- Protocol with Join, Sync, Task, Election messages
- Agent roles: Coordinator, Worker, Scout, Specialist

Binaries:
- edge-demo: Demo of distributed learning
- edge-agent: CLI agent that joins swarm
- edge-coordinator: Swarm coordinator

Dependencies:
- ruv-swarm-transport v1.0.5
- tokio, serde, lz4_flex, clap
 2025-12-31 17:20:51 +00:00
Claude
3fcdbe48c1 perf(neural-trader): optimize backtesting and risk management 
Backtesting:
- Single-pass metrics calculation (was 10+ passes)
- Inline stats: mean, variance, win/loss counts computed together
- Combined drawdown metrics in one pass
- Removed redundant method calls

Risk Management:
- Ring buffers for trade history (O(1) vs O(n) shift/slice)
- Running sum for volatility average (O(1) vs O(n) reduce)
- Incremental loss count tracking

Reduces iteration overhead by ~5-10x for large datasets.
 2025-12-31 17:19:03 +00:00
Claude
65e792f24c perf(neural-trader): optimize backtesting and risk management 
Backtesting:
- Single-pass metrics calculation (was 10+ passes)
- Inline stats: mean, variance, win/loss counts computed together
- Combined drawdown metrics in one pass
- Removed redundant method calls

Risk Management:
- Ring buffers for trade history (O(1) vs O(n) shift/slice)
- Running sum for volatility average (O(1) vs O(n) reduce)
- Incremental loss count tracking

Reduces iteration overhead by ~5-10x for large datasets.
 2025-12-31 17:19:03 +00:00
Claude
bca9855278 feat(neural-trader): add integrated trading system 
Components:
- DAG-based trading pipeline (4.6ms latency)
  • Parallel execution of LSTM, Sentiment, DRL
  • Signal fusion with configurable weights
  • Kelly-based position sizing

- Backtesting framework
  • Sharpe, Sortino, Calmar ratios
  • Max drawdown, VaR, CVaR
  • Walk-forward analysis
  • Comprehensive trade statistics

- Real data connectors
  • Yahoo Finance (free, historical)
  • Alpha Vantage (sentiment, intraday)
  • Binance (crypto, WebSocket)
  • Rate limiting, caching, retry logic

- Risk management layer
  • Position limits (10% max per position)
  • Stop-losses (fixed, trailing, volatility)
  • Circuit breakers (drawdown, loss rate)
  • Exposure management (leverage control)
 2025-12-31 17:02:40 +00:00
Claude
69d63cc4b8 feat(neural-trader): add integrated trading system 
Components:
- DAG-based trading pipeline (4.6ms latency)
  • Parallel execution of LSTM, Sentiment, DRL
  • Signal fusion with configurable weights
  • Kelly-based position sizing

- Backtesting framework
  • Sharpe, Sortino, Calmar ratios
  • Max drawdown, VaR, CVaR
  • Walk-forward analysis
  • Comprehensive trade statistics

- Real data connectors
  • Yahoo Finance (free, historical)
  • Alpha Vantage (sentiment, intraday)
  • Binance (crypto, WebSocket)
  • Rate limiting, caching, retry logic

- Risk management layer
  • Position limits (10% max per position)
  • Stop-losses (fixed, trailing, volatility)
  • Circuit breakers (drawdown, loss rate)
  • Exposure management (leverage control)
 2025-12-31 17:02:40 +00:00
rUv
43169eb226 feat: add batch learning and real-time subscriptions 
New CLI Commands:
- batch-learn: Process multiple learning experiences at once
- subscribe: Stream real-time learning updates (polling)
- watch: Auto-learn from file changes in real-time

New MCP Tools (49 total):
- hooks_batch_learn: Batch process experiences array
- hooks_subscribe_snapshot: Get state deltas for subscriptions
- hooks_watch_status: Get current watch/learning status

Features:
- Batch learning processes multiple experiences efficiently
- Subscribe streams events: learn, route, memory, compress
- Watch monitors file changes and auto-learns patterns
- Co-edit detection in watch mode (files edited within 1 min)

Published as v0.1.71
 2025-12-31 16:02:29 +00:00
rUv
e08714dd44 feat: add batch learning and real-time subscriptions 
New CLI Commands:
- batch-learn: Process multiple learning experiences at once
- subscribe: Stream real-time learning updates (polling)
- watch: Auto-learn from file changes in real-time

New MCP Tools (49 total):
- hooks_batch_learn: Batch process experiences array
- hooks_subscribe_snapshot: Get state deltas for subscriptions
- hooks_watch_status: Get current watch/learning status

Features:
- Batch learning processes multiple experiences efficiently
- Subscribe streams events: learn, route, memory, compress
- Watch monitors file changes and auto-learns patterns
- Co-edit detection in watch mode (files edited within 1 min)

Published as v0.1.71
 2025-12-31 16:02:29 +00:00
rUv
7b3b8a2f30 fix: defensive checks for Q-learning patterns and data loading 
- Add null checks in getQ() method for patterns object
- Add null checks in updateQ() and learn() methods
- Improve load() to merge file data with defaults
- Ensures all required fields exist even with partial data
- Fixes 'Cannot read properties of undefined' errors

Published as v0.1.70
 2025-12-31 15:40:29 +00:00
rUv
2b4f809ceb fix: defensive checks for Q-learning patterns and data loading 
- Add null checks in getQ() method for patterns object
- Add null checks in updateQ() and learn() methods
- Improve load() to merge file data with defaults
- Ensures all required fields exist even with partial data
- Fixes 'Cannot read properties of undefined' errors

Published as v0.1.70
 2025-12-31 15:40:29 +00:00
rUv
be0829200e feat: Full v2.1 upgrade with multi-algorithm learning and TensorCompress (v0.1.69) 
## Multi-Algorithm Learning Engine
- 9 algorithms: q-learning, sarsa, double-q, actor-critic, ppo, decision-transformer, monte-carlo, td-lambda, dqn
- Task-specific configuration:
  - agent-routing: double-q (reduces bias)
  - error-avoidance: sarsa (conservative)
  - confidence-scoring: actor-critic (continuous)
  - trajectory-learning: decision-transformer (sequence)
  - context-ranking: ppo (stable)
  - memory-recall: td-lambda (traces)

## TensorCompress (10x Memory Savings)
- 5 compression levels based on access frequency:
  - none (hot >0.8): 0% savings
  - half (warm >0.4): 50% savings
  - pq8 (cool >0.1): 87.5% savings
  - pq4 (cold >0.01): 93.75% savings
  - binary (archive ≤0.01): 96.9% savings
- Auto-compression on session-end

## Pretrain Phases (11 total)
- Phase 10: Multi-algorithm learning bootstrap
- Phase 11: TensorCompress initialization

## Environment Variables (v2.1)
- RUVECTOR_MULTI_ALGORITHM=true
- RUVECTOR_DEFAULT_ALGORITHM=double-q
- RUVECTOR_TENSOR_COMPRESS=true
- RUVECTOR_AUTO_COMPRESS=true

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 15:24:30 +00:00
rUv
58738f8cad feat: Full v2.1 upgrade with multi-algorithm learning and TensorCompress (v0.1.69) 
## Multi-Algorithm Learning Engine
- 9 algorithms: q-learning, sarsa, double-q, actor-critic, ppo, decision-transformer, monte-carlo, td-lambda, dqn
- Task-specific configuration:
  - agent-routing: double-q (reduces bias)
  - error-avoidance: sarsa (conservative)
  - confidence-scoring: actor-critic (continuous)
  - trajectory-learning: decision-transformer (sequence)
  - context-ranking: ppo (stable)
  - memory-recall: td-lambda (traces)

## TensorCompress (10x Memory Savings)
- 5 compression levels based on access frequency:
  - none (hot >0.8): 0% savings
  - half (warm >0.4): 50% savings
  - pq8 (cool >0.1): 87.5% savings
  - pq4 (cold >0.01): 93.75% savings
  - binary (archive ≤0.01): 96.9% savings
- Auto-compression on session-end

## Pretrain Phases (11 total)
- Phase 10: Multi-algorithm learning bootstrap
- Phase 11: TensorCompress initialization

## Environment Variables (v2.1)
- RUVECTOR_MULTI_ALGORITHM=true
- RUVECTOR_DEFAULT_ALGORITHM=double-q
- RUVECTOR_TENSOR_COMPRESS=true
- RUVECTOR_AUTO_COMPRESS=true

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 15:24:30 +00:00
rUv
cff643136a fix: robust sessionEnd with full data structure validation (v0.1.68) 
- Check this.data exists before accessing properties
- Initialize trajectories array if missing
- Add try/catch around engine and save operations
- Null-check trajectory objects in filter

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 15:17:35 +00:00
rUv
af4e3756f6 fix: robust sessionEnd with full data structure validation (v0.1.68) 
- Check this.data exists before accessing properties
- Initialize trajectories array if missing
- Add try/catch around engine and save operations
- Null-check trajectory objects in filter

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 15:17:35 +00:00
rUv
3b99b3efb7 fix: handle undefined stats in sessionEnd (v0.1.67) 
- Add defensive check for this.data.stats
- Initialize with defaults if missing
- Fixes "Cannot read properties of undefined (reading 'last_session')"

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 15:15:45 +00:00
rUv
bd6a775de2 fix: handle undefined stats in sessionEnd (v0.1.67) 
- Add defensive check for this.data.stats
- Initialize with defaults if missing
- Fixes "Cannot read properties of undefined (reading 'last_session')"

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 15:15:45 +00:00
rUv
8e8f952133 feat: add TensorCompress and multi-algorithm LearningEngine (v0.1.66) 
TensorCompress:
- Adaptive tensor compression with 5 levels (none, half, pq8, pq4, binary)
- Access-frequency based auto-compression
- Up to 10x memory savings for pattern storage
- CLI: compress, compress-stats, compress-store, compress-get
- MCP: hooks_compress, hooks_compress_stats, hooks_compress_store, hooks_compress_get

LearningEngine (9 algorithms):
- Q-Learning: Simple off-policy (default)
- SARSA: On-policy, conservative (error-avoidance)
- Double Q-Learning: Reduces overestimation (precise routing)
- Actor-Critic: Policy gradient + value (confidence scoring)
- PPO: Stable policy updates (preference learning)
- Decision Transformer: Sequence modeling (trajectory patterns)
- Monte Carlo: Full episode learning (unbiased estimates)
- TD(λ): Eligibility traces (credit assignment)
- DQN: Experience replay (high-dim states)

CLI Commands:
- learning-config: Configure algorithms per task
- learning-stats: View algorithm performance
- learning-update: Record experiences
- learn: Combined action + recommendation

MCP Tools:
- hooks_learning_config, hooks_learning_stats
- hooks_learning_update, hooks_learn
- hooks_algorithms_list

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 15:13:13 +00:00
rUv
4953d1d5ac feat: add TensorCompress and multi-algorithm LearningEngine (v0.1.66) 
TensorCompress:
- Adaptive tensor compression with 5 levels (none, half, pq8, pq4, binary)
- Access-frequency based auto-compression
- Up to 10x memory savings for pattern storage
- CLI: compress, compress-stats, compress-store, compress-get
- MCP: hooks_compress, hooks_compress_stats, hooks_compress_store, hooks_compress_get

LearningEngine (9 algorithms):
- Q-Learning: Simple off-policy (default)
- SARSA: On-policy, conservative (error-avoidance)
- Double Q-Learning: Reduces overestimation (precise routing)
- Actor-Critic: Policy gradient + value (confidence scoring)
- PPO: Stable policy updates (preference learning)
- Decision Transformer: Sequence modeling (trajectory patterns)
- Monte Carlo: Full episode learning (unbiased estimates)
- TD(λ): Eligibility traces (credit assignment)
- DQN: Experience replay (high-dim states)

CLI Commands:
- learning-config: Configure algorithms per task
- learning-stats: View algorithm performance
- learning-update: Record experiences
- learn: Combined action + recommendation

MCP Tools:
- hooks_learning_config, hooks_learning_stats
- hooks_learning_update, hooks_learn
- hooks_algorithms_list

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 15:13:13 +00:00
Claude
30f5f25ada perf(neural-trader): optimize LSTM, attention, and sentiment 
- LSTM: pre-allocate gate vectors, inline sigmoid/tanh (avoid map/reduce)
- MultiHeadAttention: cache-friendly i-k-j matmul, optimized softmax
- FeedForward: pre-allocate hidden layer, manual loops
- LayerNorm: manual mean/variance computation
- Lexicon: char-based word extraction (avoid regex)

Key improvements:
- Buffer push: 1.1M/s (+67%)
- Buffer sample: 319K/s (+22%)
- Lexicon: 346K/s (+16%)
 2025-12-31 14:19:27 +00:00
Claude
8873f28075 perf(neural-trader): optimize LSTM, attention, and sentiment 
- LSTM: pre-allocate gate vectors, inline sigmoid/tanh (avoid map/reduce)
- MultiHeadAttention: cache-friendly i-k-j matmul, optimized softmax
- FeedForward: pre-allocate hidden layer, manual loops
- LayerNorm: manual mean/variance computation
- Lexicon: char-based word extraction (avoid regex)

Key improvements:
- Buffer push: 1.1M/s (+67%)
- Buffer sample: 319K/s (+22%)
- Lexicon: 346K/s (+16%)
 2025-12-31 14:19:27 +00:00
Claude
920ae74312 feat(neural-trader): add production modules with benchmarks 
- Add Fractional Kelly engine (1/5th Kelly, 576K ops/s)
- Add Hybrid LSTM-Transformer predictor (1.8K predictions/s)
- Add DRL Portfolio Manager (PPO/SAC/A2C ensemble, 17K ops/s)
- Add Sentiment Alpha pipeline (3.7K signals/s)
- Add comprehensive benchmark suite and documentation

All modules production-ready with sub-millisecond latency.
 2025-12-31 14:12:41 +00:00
Claude
88f6fdd0b2 feat(neural-trader): add production modules with benchmarks 
- Add Fractional Kelly engine (1/5th Kelly, 576K ops/s)
- Add Hybrid LSTM-Transformer predictor (1.8K predictions/s)
- Add DRL Portfolio Manager (PPO/SAC/A2C ensemble, 17K ops/s)
- Add Sentiment Alpha pipeline (3.7K signals/s)
- Add comprehensive benchmark suite and documentation

All modules production-ready with sub-millisecond latency.
 2025-12-31 14:12:41 +00:00
Claude
beb6403bed perf(neural-trader): benchmark suite and additional optimizations 
Added benchmark.js performance suite measuring:
- GNN correlation matrix construction
- Matrix multiplication (original vs optimized)
- Object pooling vs direct allocation
- Ring buffer vs Array.shift()
- Softmax function performance

Additional optimizations:
- attention-regime-detection.js: Optimized softmax avoids spread operator,
  uses loop-based max finding and single-pass exp+sum (2x speedup)
- gnn-correlation-network.js: Pre-computed statistics for Pearson correlation
  via precomputeStats() and calculateCorrelationFast() methods. Avoids
  recomputing mean/std for each pair. Spearman rank also optimized.

Benchmark results:
- Cache-friendly matmul: 1.7-2.9x speedup
- Object pooling: 2.7x speedup
- Ring buffer: 12-14x speedup
- Optimized softmax: 2x speedup
 2025-12-31 06:15:53 +00:00
Claude
4865218ca9 perf(neural-trader): benchmark suite and additional optimizations 
Added benchmark.js performance suite measuring:
- GNN correlation matrix construction
- Matrix multiplication (original vs optimized)
- Object pooling vs direct allocation
- Ring buffer vs Array.shift()
- Softmax function performance

Additional optimizations:
- attention-regime-detection.js: Optimized softmax avoids spread operator,
  uses loop-based max finding and single-pass exp+sum (2x speedup)
- gnn-correlation-network.js: Pre-computed statistics for Pearson correlation
  via precomputeStats() and calculateCorrelationFast() methods. Avoids
  recomputing mean/std for each pair. Spearman rank also optimized.

Benchmark results:
- Cache-friendly matmul: 1.7-2.9x speedup
- Object pooling: 2.7x speedup
- Ring buffer: 12-14x speedup
- Optimized softmax: 2x speedup
 2025-12-31 06:15:53 +00:00
rUv
5c2ca21fb9 docs: update README with v2.0 features 
- Add Claude Code Intelligence v2.0 section with MCP tools
- Add ONNX WASM embeddings documentation
- Add Windows installation with --ignore-scripts
- Add new CLI commands (AST, Diff, Coverage, Graph, Security, RAG)
- Update hooks configuration with new env variables
- Add performance comparison table (40,000x cache speedup)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 06:13:35 +00:00
rUv
9b2c561c97 docs: update README with v2.0 features 
- Add Claude Code Intelligence v2.0 section with MCP tools
- Add ONNX WASM embeddings documentation
- Add Windows installation with --ignore-scripts
- Add new CLI commands (AST, Diff, Coverage, Graph, Security, RAG)
- Update hooks configuration with new env variables
- Add performance comparison table (40,000x cache speedup)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 06:13:35 +00:00
rUv
eca6ca7981 feat: add comprehensive intelligence layer with ONNX, AST, Graph, and Coverage modules 
Core Modules Added:
- ast-parser.ts: Full AST parsing with symbol extraction, complexity analysis
- onnx-embedder.ts: ONNX WASM embeddings with SIMD acceleration
- diff-embeddings.ts: Semantic diff analysis with risk scoring
- coverage-router.ts: Test coverage-aware agent routing
- graph-algorithms.ts: MinCut, Spectral clustering, Louvain communities
- graph-wrapper.ts: Code dependency graph builder
- cluster-wrapper.ts: RuVector cluster management
- router-wrapper.ts: Semantic routing wrapper
- parallel-intelligence.ts: Parallel processing orchestration
- parallel-workers.ts: Worker pool with work stealing

CLI Hooks (13 new commands):
- ast-analyze, ast-complexity
- diff-analyze, diff-classify, diff-similar
- coverage-route, coverage-suggest
- graph-mincut, graph-cluster
- security-scan, rag-context, git-churn, route-enhanced

MCP Server (16 new tools):
- hooks_ast_*, hooks_diff_*, hooks_coverage_*
- hooks_graph_*, hooks_security_*, hooks_rag_*
- hooks_attention_info, hooks_gnn_info

Enhanced Features:
- 10 attention mechanisms (Flash, Hyperbolic, MoE, GraphRoPe, etc.)
- 9-phase pretrain with neural capabilities
- ONNX WASM runtime (7.4MB) with all-MiniLM-L6-v2 support
- hooks init generates v2.0 templates with full documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 06:05:38 +00:00
rUv
52ded6e0e6 feat: add comprehensive intelligence layer with ONNX, AST, Graph, and Coverage modules 
Core Modules Added:
- ast-parser.ts: Full AST parsing with symbol extraction, complexity analysis
- onnx-embedder.ts: ONNX WASM embeddings with SIMD acceleration
- diff-embeddings.ts: Semantic diff analysis with risk scoring
- coverage-router.ts: Test coverage-aware agent routing
- graph-algorithms.ts: MinCut, Spectral clustering, Louvain communities
- graph-wrapper.ts: Code dependency graph builder
- cluster-wrapper.ts: RuVector cluster management
- router-wrapper.ts: Semantic routing wrapper
- parallel-intelligence.ts: Parallel processing orchestration
- parallel-workers.ts: Worker pool with work stealing

CLI Hooks (13 new commands):
- ast-analyze, ast-complexity
- diff-analyze, diff-classify, diff-similar
- coverage-route, coverage-suggest
- graph-mincut, graph-cluster
- security-scan, rag-context, git-churn, route-enhanced

MCP Server (16 new tools):
- hooks_ast_*, hooks_diff_*, hooks_coverage_*
- hooks_graph_*, hooks_security_*, hooks_rag_*
- hooks_attention_info, hooks_gnn_info

Enhanced Features:
- 10 attention mechanisms (Flash, Hyperbolic, MoE, GraphRoPe, etc.)
- 9-phase pretrain with neural capabilities
- ONNX WASM runtime (7.4MB) with all-MiniLM-L6-v2 support
- hooks init generates v2.0 templates with full documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 06:05:38 +00:00