Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1
No description provided.
Self-Optimizing Neural Architecture (SONA) - Runtime-adaptive learning with LoRA, EWC++, and ReasoningBank for LLM routers and AI systems. Sub-millisecond learning overhead, WASM and Node.js support.
Rust language support for the CodeMirror code editor
Rust dictionary for cspell.
Self-learning vector database for Node.js — hybrid search, Graph RAG, FlashAttention-3, HNSW, 50+ attention mechanisms
Super-fast alternative for babel
Lezer-based Rust grammar
Complete WASM toolkit for edge AI: vector search, graph DB, neural networks, DAG workflows, SQL/SPARQL/Cypher, and ONNX inference - all running in browser
Generates and consumes source maps
Ultra-fast MicroLoRA adaptation for WASM - rank-2 LoRA with <100us latency for per-operator learning
Welcome to the [Node.js] binding for the Rust [`matrix-sdk-crypto`] library! This binding is part of the [`matrix-rust-sdk`] project, which is a library implementation of a [Matrix] client-server.
Rust grammar for tree-sitter
A conversational AI-driven telecom multi-agent system for managing call balances, push notifications, marketing, targeting, and sales.
High-performance neural trading system with complete NAPI API (178 functions), advanced CLI with interactive mode, GPU acceleration, real-time execution, multi-agent swarm coordination, neural networks, risk management, sports betting, syndicate collabora
Queue for messages and jobs based on Redis
Browser automation CLI for AI agents
A high-performance utilities for WhatsApp, powered by Rust and WebAssembly.
Create cross-toolchain from https://github.com/rust-cross/manylinux-cross/tree/main
A simple toolkit for building scalable and maintainable applications
Fast JavaScript/TypeScript bundler in Rust with Rollup-compatible API.
JSON Schema Meta Schema & Generated types for typescript, rust, golang and python
Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference
(De)serialization functions for the Cardano blockchain along with related utility functions