Context retrieval for DeepSeek Harness: ranks docs, code and media by relevance into a sidebar Context Pack. Lexical and fully local by default. Hybrid is off until you configure a provider; it sends your query and file titles/summaries, not bodies.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.