chenzheshushi-commits/dsh-evolve0

dsh-evolve

自进化记忆与技能生命周期插件:支持跨会话零 Token 确定性召回、分级审批门及技能文件提炼。

AI 分析

核心用途是构建智能体的长期记忆与技能积累。适合希望智能体能够“越用越聪明”、自动将重复的流程提炼为持久化技能文件(SKILL.md)的深度用户。

套件
dsh-evolve
版本
0.4.1
授權
MIT
最近更新
2026年8月23日

安裝

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chenzheshushi-commits/dsh-evolve

Configuration

Everything is configurable through the plugin's settings page (web profile) or your DSH config. Notable switches:

KeyDefaultEffect
autoConfirmEnabledtruefalse = every model write waits for review
reviewEnabledtrueBackground per-turn review
reviewEveryTurns5Review throttle
reviewModel(main model)Route review to a different model
refineLLMfalseUse an LLM pass when crystallizing/refining skills
reinforceEvery3Observations per importance step
memoryMaxChars20000Memory character budget (0 disables)
convergeSuggesttrueSurface merge/fold suggestions
curatorStaleDays / curatorArchiveDays30 / 60Skill lifecycle thresholds
ftsEnabledtruefalse = pure bigram recall, no SQLite

The LLM is only ever used for optional auxiliary passes — skill refinement, background review, and skill merging. All of them are single-shot, skippable, and fall back to deterministic behavior on failure. Nothing runs in your main loop.