cocoplus

Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

LLM Frontend for Power Users.