プラグイン

AI エージェント向け LLM 監督型の永続メモリ — グラフベースの想起、セッションをまたぐ知識、シングルバイナリ。DeepSeek Harness、Claude Code、OpenClaw、その他あらゆるエージェントランタイムで動作。

Curated file-based long-term memory for DeepSeek Harness — human-readable markdown notes, one plain-file store shared across hosts (git-ignored when it lives inside a project repo), and a deterministic index cap enforced by ctx.tools.guard()

The Engramory curated-memory discipline as an installable plugin ([npm: dsh-engramory](https://www.npmjs.com/package/dsh-engramory)): a deterministic 200-line / 25 KB cap on the `MEMORY.md` index via `ctx.tools.guard()` — growth denied, a shrinking rewrite always passes — plus the protocol registered as a runtime skill. The store is plain markdown, one file per fact, shared with Claude Code, Codex, Kiro, and OpenClaw.

Mnemon との深い統合: ローカルの 3 階層メモリ（Runtime Memory、検索可能な Documents、監督下の Memory Spaces）。

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.