- Add performance badges: 10K records in 53ms, 150x faster
- Detailed benchmark table: 1ms (100) to 53ms (10K records)
- Per-data-type benchmarks: Bloomberg 12ms, Medical 15ms
- Comparison vs traditional tools: Faker.js ~800ms, Python ~1200ms
- Add AI Memory Engine integration section with code example
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Rewrite intro with clear 'What Is This?' explanation
- Add 'Who Is This For?' user type table
- Add visual 'How It Works' diagram
- Add '9 Trading Modes' comparison table
- Add 'Feature Comparison' vs traditional methods
- Add 'Strategy Benchmarks' with win rates and Sharpe ratios
- Add 'Technical Capabilities' summary table
- Add 'Performance Specs' benchmarks
- Add 'Supported Markets' with data sources
- Remove duplicate sections from later in document
- Remove emojis from enumTitles that may break UI parsing
- Add prefill property to all fields for proper default display
- Add detailed description text for every field with help info
- Organize into 11 logical sections with sectionCaption/Description
- Set optimized default values for all 60+ parameters
- Ensure proper editor types for all fields (number, select, checkbox)
- Add integrate_trading action for AI trading signal integration
- Add Trading Integration UI section in input_schema.json
- Support live mode (call Neural Trader actor) and simulated mode
- Store trading signals as searchable memories
- Add trading history search via semantic similarity
- Support multiple strategies: ensemble, neural_momentum, lstm_prediction, transformer_attention, reinforcement
- Fix apifyToken variable scope issue
Build 1.0.26 deployed to Apify.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds backtest, sports_betting, prediction_markets, and arbitrage modes
to the Apify input schema for Actor validation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements all missing modes from input schema:
- sports_betting: Kelly Criterion, The Odds API, arbitrage detection
- prediction_markets: Polymarket API, probability modeling
- arbitrage: Cross-exchange crypto, DeFi opportunities
- backtest: Historical simulation, Monte Carlo confidence intervals
- train: Gradient descent neural network training, early stopping
- analyze: Deep technical analysis, pattern recognition, Fibonacci
- live: Alpaca API integration, dry run mode
Each mode includes comprehensive routing in Actor.main with proper
error handling and output formatting.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add metadata field to JsVectorEntry, JsSearchResult, JsSearchQuery
- Metadata stored as JSON string in native layer
- Add filter support for metadata-based search
- Update ruvector wrapper with auto JSON conversion
- Users can now pass metadata objects directly
Published:
- ruvector-core-linux-x64-gnu@0.1.26
- @ruvector/core@0.1.28
- ruvector@0.1.35
Fixes#71🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added title and description to all nested object properties
- Fixed confidenceLevel type from number to string for select editor
- Fixed patterns editor from stringList to select with enum
- Removed neural-trader native dependency from neural-trader-system
All 6 actors now successfully deployed to Apify:
- AI Trading Simulator (N1s3iuVcCrz5wcnoV)
- Agent Training Factory (qP6kNaWoD6VqpwhZr)
- Market Research Swarm (PVyyfXAwFMRqfwCuC)
- Financial Stress Test (7K3WQwvPHq2h7iyE8)
- RAG Knowledge Builder (Dhtq8JwapevaRtgAw)
- Neural Trader System (BizYfvSOLAmZdIUD2)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added sectionCaption and sectionDescription for organized UI groups
- Added prefill, unit, and nullable properties
- Enhanced enumTitles with descriptive labels and emoji icons
- Fixed @huggingface/transformers version (^2.0.0 → ^3.0.0)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add agentic-synth actor with TRM/SONA self-learning
- Integrate 13 popular Apify scrapers for data grounding
- Add 6 use case templates (lead-intelligence, competitor-monitor, etc.)
- Include MCP server for AI agent integration
- Add comprehensive README with tutorials and SEO optimization
- Support generate/integrate/template modes
- Add webhook and embedding generation support
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a new RuvLLM section to the rvlite dashboard with:
- TRM (Tiny Recursive Models) configuration
- MicroLoRA settings for instant per-request adaptation
- BaseLoRA settings for background training
- ONNX model loading interface
- Test playground with feedback buttons
The dashboard source is now tracked in git to prevent loss.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds the original rvlite dashboard to version control to prevent
accidental loss. Includes:
- Dashboard UI assets (React build)
- RvLite WASM bindings
- CLI entry point for 'npx @ruvector/rvlite serve'
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add NaN protection to sigmoid activation with -20/20 clamping (mlp.rs)
- Add NaN protection to confidence scoring output (confidence.rs)
- Implement mean_pool_into for zero-allocation pooling (engine.rs)
- Reuse latent buffer across iterations using std::mem::take
- Pre-allocate answer pooling buffer in reasoning loop
- Mark use_simd config as reserved for future implementation
These optimizations reduce heap allocations in the hot path and
prevent potential NaN propagation from unbounded exp() operations.
All 63 tests pass with no regressions.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Attribution: Based on Samsung SAIL Montreal's TinyRecursiveModels
Repository: https://github.com/SamsungSAILMontreal/TinyRecursiveModels
This commit adds a complete TRM implementation for recursive reasoning:
## Core Components
- TrmConfig: Configuration with builder pattern, validation, serde support
- TrmEngine: Main recursive reasoning engine with K iterations
- MlpLatentUpdater: Fast MLP-based latent state updates with gated residual
- AttentionLatentUpdater: Expressive multi-head cross-attention variant
- AnswerRefiner: Answer refinement with residual connections
- ConfidenceScorer: Confidence estimation with optional entropy adjustment
- SonaBridge: SONA integration for adaptive K selection and learning
## Features
- Configurable hidden/embedding dimensions (default 256)
- K iterations (1-20) with n latent updates per iteration
- Early stopping based on confidence threshold
- Convergence detection via plateau monitoring
- Trajectory recording for analysis and learning
- Variable-length input handling via mean pooling
- Thread-safe design with pre-allocated buffers
## Testing
- 59 unit tests covering all components
- 16 integration tests for full pipeline
- Benchmark suite for performance measurement
## Architecture
MLP variant: ~2-3x faster, good for simple queries
Attention variant: More expressive, better for complex reasoning
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add 03_ARCHITECTURE.md with component design and interfaces
- Add 04_REFINEMENT.md with TDD implementation plan
- Add 05_COMPLETION.md with integration testing and release process
- Add 06_BENCHMARKS.md with performance targets and validation
Comprehensive TRM integration planning following SPARC methodology
- Add 00_OVERVIEW.md with attribution to Samsung SAIL Montreal
- Add 01_SPECIFICATION.md with requirements analysis
- Add 02_PSEUDOCODE.md with algorithm design
- Include TRM recursive reasoning algorithm
- Include SONA integration algorithms
- Include SIMD optimization pseudocode
- Include WASM compilation considerations
Part of RuvLLM v2.0.0 TRM integration planning
Resolved conflict in crates/ruvector-gnn/src/training.rs by keeping PR #63's implementation which includes:
- EPS and MAX_GRAD constants for numerical stability
- Comprehensive documentation with examples
- Gradient clipping to prevent explosion
- Empty array validation
- Separate forward/backward methods
- 20 comprehensive loss function tests
* chore: Add proptest regression data from test run
Records edge cases found during property testing that cause
integer overflow failures. These will help reproduce and fix
the boundary condition bugs in distance calculations.
* fix: Resolve property test failures with overflow handling
- Fix ScalarQuantized::distance() i16 overflow: use i32 for diff*diff
(255*255=65025 overflows i16 max of 32767)
- Fix ScalarQuantized::quantize() division by zero when all values equal
(handle scale=0 case by defaulting to 1.0)
- Bound vector_strategy() to -1000..1000 range to prevent overflow in
distance calculations with extreme float values
All 177 tests now pass in ruvector-core.
* fix(cli): Resolve short option conflicts in clap argument definitions
- Change --dimensions from -d to -D to avoid conflict with global --debug
- Change --db from -d to -b across all subcommands (Insert, Search, Info,
Benchmark, Export, Import) to avoid conflict with global --debug
Fixes clap panic in debug builds: "Short option names must be unique"
Note: 4 CLI integration tests still fail due to pre-existing issue where
VectorDB doesn't persist its configuration to disk. When reopening a
database, dimensions are read from config defaults (384) instead of
from the stored database metadata. This is an architectural issue
requiring VectorDB changes to implement proper metadata persistence.
* feat(core): Add database configuration persistence and fix CLI test
- Add CONFIG_TABLE to storage.rs for persisting DbOptions
- Implement save_config() and load_config() methods in VectorStorage
- Modify VectorDB::new() to load stored config for existing databases
- Fix dimension mismatch by recreating storage with correct dimensions
- Fix test_error_handling CLI test to use /dev/null/db.db path
This ensures database settings (dimensions, distance metric, HNSW config,
quantization) are preserved across restarts. Previously opening an existing
database would use default settings instead of stored configuration.
* fix(ruvLLM): Guard against edge cases in HNSW and softmax
- memory.rs: Fix random_level() to handle r=0 (ln(0) = -inf)
- memory.rs: Fix ml calculation when hnsw_m=1 (ln(1) = 0 → div by zero)
- router.rs: Add division-by-zero guard in softmax for larger arrays
These edge cases could cause undefined behavior or NaN propagation.
* feat(attention): Implement novel Lorentz Cascade Attention (LCA)
A new hyperbolic attention architecture with significant improvements:
## Key Innovations
1. **Lorentz Model**: Uses hyperboloid instead of Poincaré ball
- No boundary instability (points can extend to infinity)
- Simpler distance formula
2. **Busemann Scoring**: O(d) attention weights via dot products
- 50-100x faster than Poincaré distance computation
- Naturally hierarchical (measures "depth" in tree)
3. **Einstein Midpoint**: Closed-form hyperbolic centroid
- 322x faster than iterative Fréchet mean (50 iterations)
- O(n×d) instead of O(n×d×iter)
4. **Multi-Curvature Heads**: Adaptive hierarchy depth
- Different heads for shallow vs deep hierarchies
- Logarithmically-spaced curvatures
5. **Cascade Aggregation**: Coarse-to-fine refinement
- Combines multi-scale representations
- Sparse attention via hierarchical pruning
## Benchmark Results (64-dim, 100 keys)
| Operation | Poincaré | LCA | Speedup |
|-----------|----------|-----|---------|
| Distance | 25 ns | 0.5 ns | 53x |
| Centroid | 2.3 ms | 7.3 µs | 322x |
## API
```rust
let lca = LorentzCascadeAttention::new(LCAConfig {
dim: 128,
num_heads: 4,
curvature_range: (0.1, 2.0),
temperature: 1.0,
});
let output = lca.attend(&query, &keys, &values);
```
Files:
- lorentz_cascade.rs: Core LCA implementation
- hyperbolic_bench.rs: Benchmark comparing LCA vs Poincaré
* feat(bench): Replace simulated Python benchmarks with real Rust benchmarks
- Delete fake qdrant_vs_ruvector_benchmark.py that used simulated data
- Add real Criterion benchmarks in benches/real_benchmark.rs
- Measure actual performance: distance ops, quantization, insert, search
- Real numbers: 16M cosine ops/sec, 2.5K searches/sec on 10K vectors
* docs: Add honest documentation about capabilities and limitations
- Update lib.rs with tested/benchmarked features vs experimental ones
- Mark AgenticDB embedding function as placeholder (NOT semantic)
- Add warning to RAG example about mock embeddings
- Clarify that external embedding models are required for semantic search
* fix: Address code review issues from gist analysis
## Fixes Applied
### 1. Fabricated Benchmarks
- Rewrote docs/benchmarks/BENCHMARK_COMPARISON.md - removed false "100-4,400x faster" claims
- Fixed benchmarks/graph/src/comparison-runner.ts - removed hardcoded latency multipliers
- Fixed benchmarks/src/results-analyzer.ts - removed simulated histogram data
### 2. Fake Text Embeddings
- Added prominent warnings to agenticdb.rs about hash-based placeholder
- Added compile-time deprecation warning in lib.rs
- Created integration guide with 4 real embedding options (ONNX, Candle, API, Python)
### 3. Incomplete GNN Training
- Implemented Loss::compute() for MSE, CrossEntropy, BinaryCrossEntropy
- Implemented Loss::gradient() for backpropagation
- Added 6 new verification tests
### 4. Distance Function Bugs
- Fixed inverted dequantization formula in ruvector-router-core (was /scale, now *scale)
- Improved scale handling in ruvector-core quantization (now uses average scale)
### 5. Empty Transaction Tests
- Implemented 10+ critical tests: dirty reads, phantom reads, MVCC, deadlock detection
- All 31 transaction tests now passing
Addresses issues from: https://gist.github.com/couzic/93126a1c12b8d77651f93a7805b4bd60🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat(embeddings): Add pluggable embedding provider system for AgenticDB
Implements a proper embedding abstraction layer to replace the hash-based placeholder:
## New Features
### EmbeddingProvider Trait
- Pluggable interface for any embedding system
- Methods: embed(), dimensions(), name()
- Thread-safe (Send + Sync)
### Built-in Providers
- **HashEmbedding**: Original placeholder (default, backward compatible)
- **ApiEmbedding**: Production-ready API providers (OpenAI, Cohere, Voyage AI)
- **CandleEmbedding**: Stub for candle-transformers (feature: real-embeddings)
### AgenticDB Updates
- New constructor: `AgenticDB::with_embedding_provider(options, provider)`
- Backward compatible: `AgenticDB::new(options)` still works with HashEmbedding
- Dimension validation ensures provider matches database configuration
### Files Added
- src/embeddings.rs: Core embedding provider system
- tests/embeddings_test.rs: Comprehensive test suite
- docs/EMBEDDINGS.md: Complete usage documentation
- examples/embeddings_example.rs: Working example
### Usage
```rust
// Production (OpenAI)
let provider = Arc::new(ApiEmbedding::openai(&key, "text-embedding-3-small"));
let db = AgenticDB::with_embedding_provider(options, provider)?;
```
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore: Bump version to 0.1.22 for crates.io publish
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore(npm): Bump all npm package versions to 0.1.22
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore: Bump version to 0.1.24
* chore: Bump version to 0.1.25 for sequential CI builds
* chore(npm): Publish v0.1.25 with updated native binaries
- Published platform packages:
- ruvector-core-linux-x64-gnu@0.1.25
- ruvector-core-linux-arm64-gnu@0.1.25
- ruvector-core-darwin-arm64@0.1.25
- ruvector-core-win32-x64-msvc@0.1.25
- @ruvector/router-linux-x64-gnu@0.1.25
- @ruvector/router-linux-arm64-gnu@0.1.25
- @ruvector/router-darwin-arm64@0.1.25
- @ruvector/router-win32-x64-msvc@0.1.25
- Published main packages:
- ruvector-core@0.1.25
- ruvector@0.1.32
- @ruvector/router@0.1.25
- @ruvector/graph-node@0.1.25
- @ruvector/graph-wasm@0.1.25
- @ruvector/cli@0.1.25
Note: darwin-x64 binaries were not built (CI cancelled)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat(embeddings): Add local embedding generation support via fastembed-rs
Implements native local embedding generation for ruvector-postgres,
eliminating the need for external embedding APIs.
New SQL functions:
- ruvector_embed(text, model) - Generate embedding from text
- ruvector_embed_batch(texts[], model) - Batch embedding generation
- ruvector_embedding_models() - List available models
- ruvector_load_model(name) - Pre-load model into cache
- ruvector_unload_model(name) - Remove model from cache
- ruvector_model_info(name) - Get model metadata
- ruvector_set_default_model(name) - Set default model
- ruvector_default_model() - Get current default
- ruvector_embedding_stats() - Get cache statistics
- ruvector_embedding_dims(model) - Get dimensions for model
Supported models:
- all-MiniLM-L6-v2 (384 dims, fast)
- BAAI/bge-small-en-v1.5 (384 dims)
- BAAI/bge-base-en-v1.5 (768 dims)
- BAAI/bge-large-en-v1.5 (1024 dims)
- sentence-transformers/all-mpnet-base-v2 (768 dims)
- nomic-ai/nomic-embed-text-v1.5 (768 dims)
Features:
- Thread-safe model caching with lazy loading
- Optional feature flag 'embeddings'
- PG17 support with updated IndexAmRoutine fields
- Updated Dockerfile for PG17 with PGDG repository
Closes#60🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* ci: Switch darwin-x64 builds from macos-13 to macos-12
The macos-13 runner appears to have availability issues causing
darwin-x64 builds to be cancelled immediately. Switching to macos-12
which should be more reliable.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(docker): Add Cargo.lock to fix dependency resolution
- Include workspace Cargo.lock in Docker build context
- Pin dependencies to avoid cargo registry parsing issues with base64ct
- Ensures reproducible builds
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* ci: Switch darwin-x64 to macos-14 runner for faster availability
macos-12 runners have very long queue times (45+ minutes).
macos-14 runners can cross-compile x86_64 binaries and have much better availability.
* feat(npm): Add darwin-x64 (Intel Mac) support
- Published ruvector-core-darwin-x64@0.1.25 with native binary built on macos-14
- Updated ruvector-core to 0.1.26 with darwin-x64 in optionalDependencies
- Updated ruvector to 0.1.33
CI runner change: Switched darwin-x64 builds from macos-12 to macos-14 for better availability.
* fix(postgres): Remove unimplemented GNN functions from SQL schema
- Removed 3 unimplemented functions: ruvector_gat_forward, ruvector_message_aggregate, ruvector_gnn_readout
- Updated Dockerfile to use pre-built SQL file instead of cargo pgrx schema (which doesn't work reliably in Docker)
- SQL function count: 92 → 89 (matching actual library exports)
- Extension now loads successfully in PostgreSQL 17 with avx2 SIMD support
- Docker image: ruvnet/ruvector-postgres:0.2.4 (477MB)
Fixes SQL/library function symbol mismatch that caused "could not find function" errors during extension loading.
* feat(postgres): Add HNSW index and embedding functions (v0.2.6)
- Added HNSW access method handler and operator classes
- Added 10 embedding generation functions (ruvector_embed, etc.)
- Removed IVFFlat references (not yet implemented)
- Updated SQL schema from 89 to 100 functions
- Fixed 'could not find function' errors on extension load
Fixes: HNSW index support, embedding generation availability
* chore: Update Cargo.lock and documentation
---------
Co-authored-by: Claude <noreply@anthropic.com>
Add MAX_GRAD constant (1e6) and clip gradients in BCE and CrossEntropy
backward passes to prevent gradient explosion with extreme prediction
values near 0 or 1.
Also add examples/loss_demo.rs for manual testing and demonstration
of loss function behavior.
Implement the previously stubbed Loss struct with compute() and gradient()
methods for all three loss types:
- Mean Squared Error (MSE): Standard regression loss
- Cross Entropy: Multi-class classification with one-hot targets
- Binary Cross Entropy: Binary/multi-label classification
Implementation details:
- Numerical stability via epsilon clamping in log/division operations
- Proper shape validation with descriptive error messages
- Empty array handling
- Comprehensive test suite with 20 new tests including:
- Basic loss computation tests
- Gradient shape and direction verification
- Numerical gradient checking
- Edge cases (empty arrays, dimension mismatches)
- Integration test with Optimizer
This enables the GNN training loop to actually compute losses and
backpropagate gradients, which was previously blocked by unimplemented!()
macros.
Published @ruvector/postgres-cli@0.2.6 to npm with PR #59 fixes:
- Use correct Docker Hub image (ruvnet/ruvector-postgres)
- Add PostgreSQL server dev headers for native builds
- Clone full repo for pgrx build instead of minimal crate
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update Docker badge to link to ruvnet/ruvector-postgres
- Update docker run command to use correct image name
- Add CLI docker install option in examples
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add amcanbuildparallel and aminsertcleanup fields to IndexAmRoutine for PG17
- Fix SQL function wrapper names to match pgrx-generated symbols
- Remove non-existent functions (GAT, message_aggregate, gnn_readout)
- Fix ruvector type I/O functions to use correct wrapper names
- Simplify Dockerfile SQL handling
Tested: Docker install works with npx @ruvector/postgres-cli install
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Published to npm with updated README documentation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
