对代理者的长期记忆是提炼而非积累的。 回忆按意义来运作，书写受证据限制，一个服务器可以保存 多个独立的存储器——每个代理模式一个——因此切换模式会切换 特工记得。

以 DeepSeek 束带插件形式发货， 一个面向其他主机的MCP服务器、一个HTTP服务和一个Python库。标准 仅限库;无向量数据库，无嵌入，无框架。

---

为什么会有这样的存在

两次失败会摧毁一个特工的长期记忆，而且是从相反的两侧扼杀。

用关键词检索会错过你需要的东西。 关于*“SSD推断的问题 芯片“* 与名为 ”通过SSD层运行2.6特斯拉型号“的内存没有任何词汇 — 但它们是同一个主体。词汇搜索没有返回任何信息;代理人回答 没有任何地方。这里的解决办法不是嵌入，而是识别*：整个索引（一行） 每个内存，以识别触发器的形式写成）被分入一个提示词和一个小型模型 命名与问题相关的内容。一个~500个记忆的索引大约相当于6k代币——一个 它位于现代上下文窗口的几百分之一，并且它位于前缀缓存中。

**写下所有东西只会毒害商店。

蒸留蔵 — distill-kura

A long-term memory for agents that is distilled, not accumulated. Recall works by meaning, writing is gated by evidence, and one server can hold several separate memories — one per agent mode — so switching mode switches what the agent remembers.

Ships as a DeepSeek Harness plugin, an MCP server for any other host, an HTTP service, and a Python library. Standard library only; no vector database, no embeddings, no framework.

        ┌── recall ──────────────────────────────────────────────┐
        │  question → names a memory? → deterministic hit   ~2 ms│
        │      else → whole index in one prompt → picked slugs   │
        │           → walk [[links]] → the neighbourhood   ~0.4 s│
        └────────────────────────────────────────────────────────┘
        ┌── distil ──────────────────────────────────────────────┐
        │  journal → classed evidence → candidates → GATE        │
        │  → new? → composed → draft → judged → poured           │
        └────────────────────────────────────────────────────────┘

---

Why this exists

Two failures kill an agent’s long-term memory, and they kill it from opposite sides.

Retrieval by keyword misses the thing you needed. A question about “SSD inference chips” shares no word with a memory titled “running the 2.6T model off an SSD tier” — yet they are the same subject. Word search returns nothing; the agent answers from nowhere. The fix here is not embeddings but recognition: the entire index (one line per memory, written as a recognition trigger) goes into one prompt, and a small model names what bears on the question. An index of ~500 memories is around 6k tokens — a few percent of a modern context window, and it sits in the prefix cache.

Writing everything poisons the store. An agent asserts something; a naive distiller records the assertion as a fact; the next agent reads it back as ground truth and repeats it with more confidence. That loop is self-reinforcing, and prompt instructions do not stop it — measured, not assumed. So the write path is gated by deterministic Python: every candidate memory must carry quotes that exist character-for-character in the raw material, tagged with where they came from.

A quote that is not found verbatim is discarded. A candidate with no surviving quote is thrown away. A number with no [TOOL] behind it is stripped. Text crediting the human with a decision, when no [USER] quote survived, is refused at the last gate. Ideas are welcome — they go to a seed file, never to the store, and graduate only when later