Commit graph

19 commits

Author SHA1 Message Date
rUv
2288e79bd8 feat(ai-memory-engine): Integrate persistence backends + add tests
Integration:
- Added storageBackend input parameter parsing
- Integrated createPersistence() into main actor flow
- Load session uses new persistence with legacy fallback
- Save session uses new persistence with legacy fallback
- Added persistence result to output metadata
- Proper connection cleanup on exit

Test Suite (tests/persistence-benchmark.js):
- Hyperbolic geometry: projection, distance, Möbius add, exp/log maps
- Binary persistence: 4.8x smaller than JSON, perfect fidelity
- Session persistence: data survives across simulated runs
- Benchmarks: 2M ops/sec Euclidean, 0.4M ops/sec hyperbolic

Results:
- Binary format: 4.8x size reduction (7.06 MB → 1.46 MB)
- Serialization: 39x faster (54ms → 1.4ms)
- All hyperbolic geometry functions verified correct

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-14 05:15:53 +00:00
rUv
fbf985dc40 feat(ai-memory-engine): Add 8 vector storage backends + hyperbolic geometry
Storage Backends:
- ApifyBinary: 4x smaller binary Float32Array storage
- PostgreSQL/Supabase/Neon: pgvector with IVFFlat indexing
- Qdrant: High-throughput cloud vector DB with filtering
- Pinecone: Serverless managed infrastructure
- Weaviate: GraphQL-based hybrid search
- LanceDB: Local embedded vector database
- Hyperbolic: Poincaré ball model for hierarchical data

Hyperbolic Geometry:
- Poincaré ball projection and distance
- Möbius addition for vector operations
- Exponential/logarithmic maps (tangent ↔ hyperbolic)
- Fréchet mean (hyperbolic centroid)
- Hyperbolic k-means clustering
- Batch distance computation (SIMD-friendly)
- Parallel transport and geodesic interpolation

Input Schema:
- storageBackend selector (8 options)
- Connection strings for Postgres/Qdrant/Pinecone/Weaviate
- Curvature parameter for hyperbolic embeddings
- Hyperbolic clustering toggle

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-14 04:12:06 +00:00
rUv
c9581a7fa6 feat(agentic-synth): Add SONA self-learning + quality improvements
- Enhanced intro with 3-tier SONA learning table
- Added 188K records/sec badge and self-learning badge
- Fixed ecommerce: real brands per category (Samsung, Nike, LEGO)
- Fixed data consistency: stock/inStock, shipping free/price
- Fixed bloomberg: consensus recommendation matches analyst ratings
- Integrated neural pattern training per data type
- Updated benchmarks: 1ms (100) → 53ms (10K)

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-14 02:53:06 +00:00
rUv
936c55f703 docs(agentic-synth): Add benchmark results and comparisons
- 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>
2025-12-14 02:42:51 +00:00
rUv
2940aadcf0 docs(neural-trader): Simplify intro with comparison tables
- 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
2025-12-14 02:08:51 +00:00
rUv
d6515bfc41 fix(neural-trader): Complete input schema rewrite for Apify UI compatibility
- 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)
2025-12-14 02:03:46 +00:00
rUv
fee8b8fb50 feat(neural-trader): Complete UI overhaul with 11 accordion sections
New sections:
- Core Settings, Risk Management, Analysis Settings
- Neural Network Configuration, Swarm Intelligence
- Technical Analysis (individual indicator toggles)
- Output & Notifications, Live Trading, Backtest
- Sports Betting, Prediction Markets, Arbitrage

New options: trailing stop, max drawdown, data source, swarm consensus,
walk-forward analysis, slippage, commission, Kelly fraction, bet types,
DeFi protocols, triangular arbitrage, max latency, and more
2025-12-13 19:56:23 +00:00
rUv
5597cc32b2 fix(neural-trader): Add editor:number to all number fields for Apify UI
Removed non-standard 'unit' property and added 'editor: number' to:
- maxPositionSize, stopLoss, takeProfit
- confidenceThreshold
- initialCapital, bankroll, minEdge
- minLiquidity, minSpread
2025-12-13 19:52:14 +00:00
rUv
c085335e43 feat(neural-trader): Add input parameters for all 9 trading modes
- Live Trading: dryRun, alpacaApiKey, alpacaSecretKey, alpacaPaper
- Backtest: initialCapital, monteCarloRuns
- Sports Betting: bankroll, minEdge, sportsLeagues, oddsApiKey
- Prediction Markets: minLiquidity, marketCategories
- Arbitrage: exchanges, minSpread, includeDeFi, includeFlashLoans
- Added UI sections for grouped parameter display
2025-12-13 19:48:51 +00:00
rUv
29c904b1b1 docs(neural-trader): Add 4 new trading modes to README
- Added backtest, sports_betting, prediction_markets, arbitrage modes
- Added new tutorials 6-9 with examples
- Updated mode parameter table with all 9 modes
- Added Advanced Trading Modes section to features
2025-12-13 19:47:21 +00:00
rUv
ee8c199fe5 fix(neural-trader): Add missing technical indicators to live mode
🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-13 19:27:13 +00:00
rUv
e7b36d1ac2 feat(ai-memory-engine): Add Neural Trader System integration
- 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>
2025-12-13 19:25:20 +00:00
rUv
487cc8afba feat(neural-trader): Add new modes to input schema
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>
2025-12-13 19:24:18 +00:00
rUv
f5154dd9e2 feat(neural-trader): Add 7 specialized trading modes
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>
2025-12-13 19:21:12 +00:00
rUv
f1ebdf853a fix(apify): Fix input schema validation for all actors
- 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>
2025-12-13 18:01:43 +00:00
rUv
53f3763937 enhance(apify): Improve input schemas with UI sections and fix npm packages
- 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>
2025-12-13 17:52:32 +00:00
rUv
b1e9c2a314 fix(apify): Correct actor.json paths for input, dockerfile, and readme
- Fixed input_schema.json paths (removed .actor/ prefix)
- Fixed Dockerfile paths (removed .actor/ prefix)
- Fixed README paths to ../README.md (parent directory)

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-13 17:48:13 +00:00
rUv
b51a0daa04 feat(apify): Add 6 new AI-powered Apify actors
New actors added to examples/apify/:

1. AI Trading Simulator
   - 4 trading strategies (mean reversion, momentum, breakout, ML neural)
   - Technical indicators (SMA, EMA, RSI, MACD, Bollinger Bands)
   - Backtesting with Sharpe/Sortino ratios, max drawdown

2. Agent Training Data Factory
   - 6 dataset types for AI agent training
   - HuggingFace-compatible output formats
   - Real-world data grounding from Apify actors

3. Market Research Swarm
   - 10 specialized agent roles
   - Multi-agent competitive intelligence
   - Consensus-based analysis

4. Financial Stress Testing
   - VaR calculation (parametric, historical, Monte Carlo)
   - 10 pre-built crisis scenarios (2008, COVID, flash crash)
   - Basel III regulatory reporting

5. RAG Knowledge Base Builder
   - 4 chunking strategies (semantic, fixed, paragraph, sentence)
   - Multiple embedding models (OpenAI, Cohere, local)
   - 6 output formats (Pinecone, Weaviate, Qdrant, Chroma, AgentDB)

6. Neural Trader System
   - LSTM, Transformer, ensemble neural strategies
   - Portfolio optimization with risk management
   - Swarm coordination for consensus predictions

All actors include:
- MCP server integration (@apify/actors-mcp-server)
- Comprehensive README with quick start guides
- SEO-optimized metadata and keywords
- ruv.io references

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-13 17:41:20 +00:00
rUv
c1f89de337 feat(apify): Add AI Synthetic Data Generator with MCP & Actor Integration
- 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>
2025-12-13 16:27:54 +00:00