dsh-continual-harness
持续自我优化闭环：持久记忆、周期评审与自动优化、跨会话共享知识、失败自动回滚，由模型可调用的 harness_refine 工具驱动。
Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.
怎么安装
dsh plugin add dsh-continual-harness 简介
dsh-continual-harness English | 中文 A **continual self-refinement plugin** for DeepSeek Harness: one plugin gives the agent a closed loop of *persistent memory + periodic review-and-refine + cross-session shared knowledge + automatic rollback on failure* (plan → validate → apply → rollback), implemented through dsh's plugin mechanisms (session events, agent-scoped events, pre-step waterfall, tools service). The design is inspired by the open-source prime-agent from Prime Intellect, a self-improving coding harness. One plugin is enough There is no need to split into multiple packages: this plugi…
推荐参考
信息
- 协议
- MIT
- 语言
- TypeScript
- GitHub 星标
- 9
- 月下载
- 1.7K
- 最近更新
- 2026-09-24
- 创建于
- 2026-08-17
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
- agent-memory, ai-agent, continual-learning, deepseek, deepseek-harness, dsh, dsh-plugin, self-evolution, self-improving-agents
同类推荐
langfuse
langfuse/langfuse
🪢 开源AI工程平台：LLM评估、可观测性、指标、提示管理、游乐场、数据集。与OpenTelemetry、LangChain、OpenAI SDK、LiteLLM等集成。🍊YC W23