https://github.com/ruvnet/ruv-fann
A blazing-fast, memory-safe neural network library for Rust that brings the power of FANN to the modern world.
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (10.7%) to scientific vocabulary
Repository
A blazing-fast, memory-safe neural network library for Rust that brings the power of FANN to the modern world.
Basic Info
- Host: GitHub
- Owner: ruvnet
- License: mit
- Language: Rust
- Default Branch: main
- Size: 163 MB
Statistics
- Stars: 252
- Watchers: 9
- Forks: 81
- Open Issues: 28
- Releases: 0
Metadata Files
README.md
ruv-FANN: The Neural Intelligence Framework 🧠
What if intelligence could be ephemeral, composable, and surgically precise?
Welcome to ruv-FANN, a comprehensive neural intelligence framework that reimagines how we build, deploy, and orchestrate artificial intelligence. This repository contains three groundbreaking projects that work together to deliver unprecedented performance in neural computing, forecasting, and multi-agent orchestration.
🌟 The Vision
We believe AI should be: - Ephemeral: Spin up intelligence when needed, dissolve when done - Accessible: CPU-native, GPU-optional - built for the GPU-poor - Composable: Mix and match neural architectures like LEGO blocks - Precise: Tiny, purpose-built brains for specific tasks
This isn't about calling a model API. This is about instantiating intelligence.
🎯 What's in This Repository?
1. ruv-FANN Core - The Foundation
A complete Rust rewrite of the legendary FANN (Fast Artificial Neural Network) library. Zero unsafe code, blazing performance, and full compatibility with decades of proven neural network algorithms.
2. Neuro-Divergent - Advanced Neural Forecasting
27+ state-of-the-art forecasting models (LSTM, N-BEATS, Transformers) with 100% Python NeuralForecast compatibility. 2-4x faster, 25-35% less memory.
3. ruv-swarm - Ephemeral Swarm Intelligence
The crown jewel. Achieves 84.8% SWE-Bench solve rate, outperforming Claude 3.7 by 14.5 points. Spin up lightweight neural networks that exist just long enough to solve problems.
🚀 Quick Install ruv-swarm
```bash
NPX - No installation required!
npx ruv-swarm@latest init --claude
NPM - Global installation
npm install -g ruv-swarm
Cargo - For Rust developers
cargo install ruv-swarm-cli ```
That's it. You're now running distributed neural intelligence.
🧠 How It Works
The Magic of Ephemeral Intelligence
- Instantiation: Neural networks are created on-demand for specific tasks
- Specialization: Each network is purpose-built with just enough neurons
- Execution: Networks solve their task using CPU-native WASM
- Dissolution: Networks disappear after completion, no resource waste
Architecture Overview
┌─────────────────────────────────────────────┐
│ Claude Code / Your App │
├─────────────────────────────────────────────┤
│ ruv-swarm (MCP/CLI) │
├─────────────────────────────────────────────┤
│ Neuro-Divergent Models │
│ (LSTM, TCN, N-BEATS, Transformers) │
├─────────────────────────────────────────────┤
│ ruv-FANN Core Engine │
│ (Rust Neural Networks) │
├─────────────────────────────────────────────┤
│ WASM Runtime │
│ (Browser/Edge/Server/Embedded) │
└─────────────────────────────────────────────┘
⚡ Key Features
🏃 Performance
- <100ms decisions - Complex reasoning in milliseconds
- 84.8% SWE-Bench - Best-in-class problem solving
- 2.8-4.4x faster - Than traditional frameworks
- 32.3% less tokens - Cost-efficient intelligence
🛠️ Technology
- Pure Rust - Memory safe, zero panics
- WebAssembly - Run anywhere: browser to RISC-V
- CPU-native - No CUDA, no GPU required
- MCP Integration - Native Claude Code support
🧬 Intelligence Models
- 27+ Neural Architectures - From MLP to Transformers
- 5 Swarm Topologies - Mesh, ring, hierarchical, star, custom
- 7 Cognitive Patterns - Convergent, divergent, lateral, systems thinking
- Adaptive Learning - Real-time evolution and optimization
📊 Benchmarks
| Metric | ruv-swarm | Claude 3.7 | GPT-4 | Improvement | |--------|-----------|------------|-------|-------------| | SWE-Bench Solve Rate | 84.8% | 70.3% | 65.2% | +14.5pp | | Token Efficiency | 32.3% less | Baseline | +5% | Best | | Speed (tasks/sec) | 3,800 | N/A | N/A | 4.4x | | Memory Usage | 29% less | Baseline | N/A | Optimal |
🌐 Ecosystem Projects
Core Projects
- ruv-FANN - Neural network foundation library
- Neuro-Divergent - Advanced forecasting models
- ruv-swarm - Distributed swarm intelligence
Tools & Extensions
- MCP Server - Claude Code integration
- CLI Tools - Command-line interface
- Docker Support - Containerized deployment
🤝 Contributing with GitHub Swarm
We use an innovative swarm-based contribution system powered by ruv-swarm itself!
How to Contribute
Fork & Clone
bash git clone https://github.com/your-username/ruv-FANN.git cd ruv-FANNInitialize Swarm
bash npx ruv-swarm init --github-swarmSpawn Contribution Agents ```bash
Auto-spawns specialized agents for your contribution type
npx ruv-swarm contribute --type "feature|bug|docs" ```
Let the Swarm Guide You
- Agents analyze codebase and suggest implementation
- Automatic code review and optimization
- Generates tests and documentation
- Creates optimized pull request
Contribution Areas
- 🐛 Bug Fixes - Swarm identifies and fixes issues
- ✨ Features - Guided feature implementation
- 📚 Documentation - Auto-generated from code analysis
- 🧪 Tests - Intelligent test generation
- 🎨 Examples - Working demos and tutorials
🙏 Acknowledgments
Special Thanks To
Core Contributors
- Ocean(@ohdearquant) - Transformed FANN from mock implementations to real neural networks with actual CPU and GPU training. Built the Rust implementation from placeholder code into a functional neural computing engine.
- Bron(@syndicate604) - Made the JavaScript/WASM integration actually work by removing mock functions and building real functionality. Transformed broken prototypes into production-ready systems.
- Jed(@jedarden) - Platform integration and scope management
- Shep(@elsheppo) - Testing framework and quality assurance
Projects We Built Upon
- FANN - Steffen Nissen's original Fast Artificial Neural Network library
- NeuralForecast - Inspiration for forecasting model APIs
- Claude MCP - Model Context Protocol for AI integration
- Rust WASM - WebAssembly toolchain and ecosystem
Open Source Libraries
- num-traits - Generic numeric traits
- ndarray - N-dimensional arrays
- serde - Serialization framework
- tokio - Async runtime
- wasm-bindgen - WASM bindings
Community
Thanks to all contributors, issue reporters, and users who have helped shape ruv-FANN into what it is today. Special recognition to the Rust ML community for pioneering memory-safe machine learning.
📄 License
Dual-licensed under: - Apache License 2.0 (LICENSE-APACHE) - MIT License (LICENSE-MIT)
Choose whichever license works best for your use case.
Owner
- Name: rUv
- Login: ruvnet
- Kind: user
- Location: 0x
- Company: Not a Bot
- Twitter: ruv
- Repositories: 86
- Profile: https://github.com/ruvnet
Unicorn Breeder.
GitHub Events
Total
- Create event: 48
- Issues event: 103
- Watch event: 162
- Delete event: 20
- Issue comment event: 353
- Member event: 1
- Push event: 178
- Gollum event: 3
- Pull request review comment event: 2
- Pull request review event: 12
- Pull request event: 95
- Fork event: 57
Last Year
- Create event: 48
- Issues event: 103
- Watch event: 162
- Delete event: 20
- Issue comment event: 353
- Member event: 1
- Push event: 178
- Gollum event: 3
- Pull request review comment event: 2
- Pull request review event: 12
- Pull request event: 95
- Fork event: 57
Committers
Last synced: 11 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| rUv | r****v@r****t | 87 |
| OceanLi | 1****t | 78 |
| syndicate604 | s****4@g****m | 64 |
| rUv Contributor | r****n@e****m | 22 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 10 months ago
All Time
- Total issues: 72
- Total pull requests: 57
- Average time to close issues: 1 day
- Average time to close pull requests: 1 day
- Total issue authors: 15
- Total pull request authors: 9
- Average comments per issue: 2.68
- Average comments per pull request: 0.63
- Merged pull requests: 15
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 72
- Pull requests: 57
- Average time to close issues: 1 day
- Average time to close pull requests: 1 day
- Issue authors: 15
- Pull request authors: 9
- Average comments per issue: 2.68
- Average comments per pull request: 0.63
- Merged pull requests: 15
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- ohdearquant (25)
- ruvnet (24)
- jedarden (5)
- Vasiliy-Bondarenko (5)
- gaberger (3)
- USEnterprises2001 (1)
- rcraw (1)
- ian-p-johnson (1)
- davidvc (1)
- ebr (1)
- elsheppo (1)
- tbowman01 (1)
- liamhelmer (1)
- coygeek (1)
- MattMagg (1)
Pull Request Authors
- ohdearquant (16)
- syndicate604 (13)
- ruvnet (11)
- jedarden (8)
- mikkihugo (4)
- farchide (2)
- ricable (1)
- mlbrilliance (1)
- bar181 (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 28
-
Total downloads:
- npm 48,853 last-month
- cargo 18,111 total
-
Total dependent packages: 0
(may contain duplicates) -
Total dependent repositories: 0
(may contain duplicates) - Total versions: 79
- Total maintainers: 3
npmjs.org: cuda-wasm
High-performance CUDA to WebAssembly/WebGPU transpiler with Rust safety - Run GPU kernels in browsers and Node.js
- Homepage: https://github.com/ruvnet/ruv-FANN/tree/main/cuda-wasm#readme
- License: MIT
-
Latest release: 1.1.1
published about 1 year ago
Rankings
Maintainers (1)
Funding
- type: github
- url: https://github.com/sponsors/ruvnet
npmjs.org: ruv-swarm
High-performance neural network swarm orchestration in WebAssembly
- Homepage: https://github.com/ruvnet/ruv-FANN#readme
- License: MIT OR Apache-2.0
-
Latest release: 1.0.18
published 12 months ago
Rankings
Maintainers (1)
crates.io: neurodna
High-performance evolutionary neural networks with genetic encoding, SIMD optimizations, and neurodivergent cognitive modeling
- Documentation: https://docs.rs/neurodna/
- License: MIT
-
Latest release: 0.0.2
published about 1 year ago
Rankings
Maintainers (1)
crates.io: ruv-swarm-daa
Decentralized Autonomous Agents (DAA) integration for ruv-swarm
- Documentation: https://docs.rs/ruv-swarm-daa/
- License: MIT
-
Latest release: 1.0.6
published about 1 year ago
Rankings
Maintainers (1)
crates.io: micro_metrics
Performance monitoring and metrics collection for micro-neural networks
- Documentation: https://docs.rs/micro_metrics/
- License: MIT OR Apache-2.0
-
Latest release: 0.2.0
published 12 months ago
Rankings
Maintainers (1)
crates.io: micro_routing
Dynamic routing and context management for micro-neural networks
- Documentation: https://docs.rs/micro_routing/
- License: MIT OR Apache-2.0
-
Latest release: 0.2.0
published 12 months ago
Rankings
Maintainers (1)
crates.io: micro_core
Core no_std Semantic Cartan Matrix implementation for rUv-FANN
- Documentation: https://docs.rs/micro_core/
- License: Apache-2.0 OR MIT
-
Latest release: 0.2.0
published 12 months ago
Rankings
Maintainers (1)
crates.io: micro_swarm
Swarm orchestration and coordination for micro-neural networks
- Documentation: https://docs.rs/micro_swarm/
- License: MIT OR Apache-2.0
-
Latest release: 0.2.0
published 12 months ago
Rankings
Maintainers (1)
crates.io: micro_cartan_attn
Complete Cartan matrix attention mechanisms with proper Lie algebra structures
- Documentation: https://docs.rs/micro_cartan_attn/
- License: MIT OR Apache-2.0
-
Latest release: 0.2.0
published 12 months ago
Rankings
Maintainers (1)
crates.io: geometric-langlands-cli
User-friendly CLI for the Geometric Langlands computational framework
- Homepage: https://github.com/ruvnet/ruv-FANN/tree/main/geometric_langlands_conjecture
- Documentation: https://docs.rs/geometric-langlands-cli/
- License: MIT
-
Latest release: 0.2.0
published 12 months ago
Rankings
Maintainers (1)
crates.io: geometric-langlands
A comprehensive computational framework for the Geometric Langlands Conjecture with neural-symbolic integration, CLI tools, WASM deployment, and CUDA acceleration
- Homepage: https://github.com/ruvnet/ruv-FANN/tree/main/geometric_langlands_conjecture
- Documentation: https://docs.rs/geometric-langlands/
- License: MIT
-
Latest release: 0.2.2
published 12 months ago
Rankings
Maintainers (1)
crates.io: ruvswarm-core
Core orchestration and agent traits for RUV Swarm
- Documentation: https://docs.rs/ruvswarm-core/
- License: MIT OR Apache-2.0
-
Latest release: 1.1.0
published about 1 year ago
Rankings
Maintainers (1)
crates.io: ruvswarm-persistence
Persistence layer with SQLite and ORM for ruvswarm
- Documentation: https://docs.rs/ruvswarm-persistence/
- License: MIT OR Apache-2.0
-
Latest release: 1.1.0
published about 1 year ago
Rankings
Maintainers (1)
crates.io: opencv-wasm
OpenCV WebAssembly bindings for browser deployment
- Documentation: https://docs.rs/opencv-wasm/
- License: Apache-2.0
-
Latest release: 4.8.1
published about 1 year ago
Rankings
Maintainers (1)
crates.io: opencv-core
OpenCV Core module - fundamental data structures and operations
- Documentation: https://docs.rs/opencv-core/
- License: Apache-2.0
-
Latest release: 4.8.1
published about 1 year ago
Rankings
Maintainers (1)
crates.io: opencv-sdk
OpenCV SDK with C/C++/Python API compatibility layer
- Documentation: https://docs.rs/opencv-sdk/
- License: Apache-2.0
-
Latest release: 4.8.1
published about 1 year ago
Rankings
Maintainers (1)
crates.io: ruvswarm-mcp
Model Context Protocol (MCP) integration for RUV Swarm
- Documentation: https://docs.rs/ruvswarm-mcp/
- License: MIT OR Apache-2.0
-
Latest release: 1.1.0
published about 1 year ago
Rankings
Maintainers (1)
crates.io: ruv-swarm-ml-training
Advanced ML training pipeline for neuro-divergent models in RUV Swarm
- Documentation: https://docs.rs/ruv-swarm-ml-training/
- License: MIT OR Apache-2.0
-
Latest release: 1.0.5
published about 1 year ago
Rankings
Maintainers (1)
crates.io: claude-parser
Claude Code CLI stream-JSON parser for ruv-swarm multi-agent orchestration
- Homepage: https://github.com/ruvnet/ruv-FANN/tree/main/ruv-swarm
- Documentation: https://docs.rs/claude-parser/
- License: MIT OR Apache-2.0
-
Latest release: 1.0.5
published about 1 year ago
Rankings
Maintainers (1)
crates.io: ruv-swarm-mcp
Model Context Protocol (MCP) integration for RUV Swarm
- Documentation: https://docs.rs/ruv-swarm-mcp/
- License: MIT OR Apache-2.0
-
Latest release: 0.2.0
published about 1 year ago
Rankings
Maintainers (1)
crates.io: ruv-swarm-agents
Specialized AI agents for RUV Swarm
- Documentation: https://docs.rs/ruv-swarm-agents/
- License: MIT OR Apache-2.0
-
Latest release: 1.0.5
published about 1 year ago
Rankings
Maintainers (1)
crates.io: ruv-swarm-ml
Machine learning integration for RUV Swarm
- Documentation: https://docs.rs/ruv-swarm-ml/
- License: MIT OR Apache-2.0
-
Latest release: 1.0.5
published about 1 year ago
Rankings
Maintainers (1)
crates.io: ruv-swarm-transport
Transport layer for RUV-FANN swarm communication with WebSocket and SharedMemory support
- Documentation: https://docs.rs/ruv-swarm-transport/
- License: MIT OR Apache-2.0
-
Latest release: 1.0.5
published about 1 year ago
Rankings
Maintainers (1)
crates.io: ruv-swarm-persistence
Persistence layer with SQLite and ORM for RUV-Swarm
- Documentation: https://docs.rs/ruv-swarm-persistence/
- License: MIT OR Apache-2.0
-
Latest release: 1.0.5
published about 1 year ago
Rankings
Maintainers (1)
crates.io: ruv-swarm-core
Core orchestration and agent traits for RUV Swarm
- Documentation: https://docs.rs/ruv-swarm-core/
- License: MIT OR Apache-2.0
-
Latest release: 1.0.6
published about 1 year ago
Rankings
Maintainers (1)
crates.io: neuro-divergent-models
Neural forecasting models implemented using ruv-FANN for time series forecasting
- Documentation: https://docs.rs/neuro-divergent-models/
- License: MIT OR Apache-2.0
-
Latest release: 0.1.0
published about 1 year ago
Rankings
Maintainers (1)
crates.io: neuro-divergent-training
Comprehensive training infrastructure for neural forecasting models
- Documentation: https://docs.rs/neuro-divergent-training/
- License: MIT OR Apache-2.0
-
Latest release: 0.1.0
published about 1 year ago
Rankings
Maintainers (1)
crates.io: ruv-fann
A pure Rust implementation of the Fast Artificial Neural Network (FANN) library
- Documentation: https://docs.rs/ruv-fann/
- License: MIT OR Apache-2.0
-
Latest release: 0.1.6
published about 1 year ago
Rankings
Maintainers (1)
Dependencies
- actions/cache v3 composite
- actions/checkout v4 composite
- benchmark-action/github-action-benchmark v1 composite
- codecov/codecov-action v3 composite
- dtolnay/rust-toolchain master composite
- dtolnay/rust-toolchain stable composite
- dtolnay/rust-toolchain nightly composite
- peaceiris/actions-gh-pages v3 composite
- 124 dependencies
- approx 0.5 development
- criterion 0.5 development
- pretty_assertions 1.4 development
- proptest 1.4 development
- bincode 1.3
- flate2 1.0
- log 0.4
- num-traits 0.2
- num_cpus 1.16
- rand 0.8
- rand_distr 0.4
- rayon 1.8
- serde 1.0
- serde_json 1.0
- thiserror 1.0