Pinned Loading

1. AffectOS AffectOS Public

   Multitask model (intent + sentiment) using DistilBERT + LoRA, reducing latency and inference cost. Unified deployment via FastAPI, optimized for production efficiency.

   Python

2. ForgeML ForgeML Public

   Production-grade MLOps reference covering the full ML lifecycle.

   Python

3. LLM-EDGE LLM-EDGE Public

   A high-performance, cost-aware Gateway for LLMs written in Rust. Designed to route requests between multiple providers (OpenAI, Anthropic, Local) with O(1) decision overhead (< 100 µs), L1 Semantic…

   Rust

4. SynapseRT SynapseRT Public

   Stateful recommendation system with incremental online learning for real-time personalization. Designed to optimize latency (P99 < 100ms) and adapt instantly to user feedback without batch retraining.

   Python

5. multimodal-rag-engine multimodal-rag-engine Public

   Multi-Modal RAG Engine is a local RAG prototype that combines hybrid (dense + sparse) search with multi-modal embeddings to retrieve text and images from complex PDFs, optimized for low-resource GP…

   Python

6. RaftKV RaftKV Public

   A fault-tolerant, consistent distributed key-value store based on Raft, ensuring high availability and durability for distributed systems.

   Rust