返回目录
Agent 与会话技能

dsh-evolve

chenzheshushi-commits/dsh-evolve

Self-evolving memory + skill lifecycle for DeepSeek Harness — durable cross-session memory with zero-token deterministic recall, tiered approval, reinforcement learning from repetition, and anti-bloat convergence for both skills and memory.

OVERVIEW

数据概览

Star
8
Fork
0
开放 Issue
0
最后推送
2026/08/31 19:27:41

PROJECT TOPICS

项目标签

PROJECT README README展开收起

正在读取 GitHub README...