DeepSeek Harness cross-session long-term memory + user profile plugin: the AI remembers who you are, your projects and preferences across sessions. Pure Markdown, zero-config, fully local. (monorepo: dsh-memory-core + dsh-memory-ui)
SpecPowers — SDD+TDD engineering methodology as a DeepSeek Harness (DSH) plugin and Claude Code skill group: 6 skills fusing OpenSpec spec-driven development with Superpowers TDD discipline into one Phase 0→4 workflow.
Assembled context for DeepSeek Harness: a context tree over the session surface with per-node assemble modes (full / key / off), agent-authored presets, and a panel that decides what the model actually sees.
dsh plugin: compiles a rough need into a versioned task book, then hands it to any AI window losslessly via a read-back handshake (/forge /relay /ack /answer /forge-list)
DeepSeek Harness（DSH）第二大脑载入器：把有硬上限、带时间戳的脑快照（身份＋状态指纹＋未决项＋指针与边界）注入每个新会话；只读、零写入、fail-loud、零依赖。 | Second Brain loader for DSH — a bounded, timestamped snapshot of your local brain in every session prompt; read-only, zero-dependency.
System-1 decision models (Jev/Laya/Kev-class) as the governance layer for an LLM agent context lifecycle: growing association graph over session segments, relevance-gated recall with Trace-as-State ordering, and plan pre-ranking — measured in solve rate, cache hit/miss tokens, cost and latency. DSH plugin + harness-agnostic proxy.
