dsh-engram
零 LLM 自动捕获 + 符号化 \[ENGRAM\] 索引渐进披露，配 ESR-lite 任务/证据闭环（esr_task / esr_node / esr_close / esr_link）、按工作区的真实使用遥测与离线召回基准（npm run eval）。
Zero-LLM auto-capture and a symbolic \[ENGRAM\] index with progressive disclosure, an ESR-lite task/evidence protocol (esr_task / esr_node / esr_close / esr_link), and per-workspace usage telemetry with an offline recall benchmark (npm run eval).
怎么安装
dsh plugin add dsh-engram 简介
dsh-engram **English · 中文** Minimalist long-term memory for DeepSeek Harness, distilled from the symbolic-index and pi-esr ideas — with one goal: **save tokens**. **Zero-LLM intake** — auto-captures meaningful events from tool results by pure pattern matching (git milestones with a written -m commit message, edits to key files, repeated errors), plus an explicit engram_store. Nothing on the hot path calls a model, and pure plumbing — git push / git stash / silent commits — is deliberately never recorded (see *Auto-capture policy* below). **Symbolic index + progressive disclosure** — a compact …
推荐参考
信息
- 协议
- MIT
- 语言
- JavaScript
- GitHub 星标
- 0
- 月下载
- –
- 最近更新
- 2026-08-24
- 创建于
- 2026-08-18
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- 主题标签
- deepseek-harness, dsh, dsh-plugin, long-term-memory, memory, pi-esr
同类推荐
hindsight
vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents
Hindsight：会学习的 Agent 长期记忆系统，自动召回/保存、知识页、深度反思与按仓库隔离的记忆银行。
memsearch
zilliztech/memsearch/tree/main/plugins/dsh
供 DSH 与其他编程 Agent 共享的 Markdown 记忆，支持自动捕获、步骤前上下文注入、搜索召回，以及通过审阅面板实现 memory-to-skill 自进化。