Explore projects in the projects → tags collection tagged with context-engineering that implement scalable context pipelines, retrieval-augmented generation (RAG), and LLM context-window optimization. This curated list highlights how organizations and open-source teams use embeddings, vector databases, prompt engineering, session/state management, knowledge graphs, and index-backed retrieval to improve relevance, latency, and cost; apply filters to narrow by language, stack, license, maturity, or benchmark metrics. Gain actionable insights on evaluation criteria—vector store selection, embedding model choice, chunking and indexing strategies, prompt templates, memory persistence, monitoring, and end-to-end cost/performance trade-offs—to compare and adopt the best context-engineering patterns. Filter the results, inspect repositories, run demos, or contribute to projects to accelerate practical context-engineering adoption in production AI systems.
