Agent 与会话技能
EverOS
EverMind-AI
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
待结构检查
agent-memoryagentic-aiaichats
REVIEW SCORECARD
评测成绩单
8.0/10Average
detail.dimSecurity9.0
detail.dimQuality6.2
detail.dimContent7.0
detail.dimDeps7.0
detail.dimMaintenance9.0
✓ 无Risky检出 · 自动化扫描结果仅供参考，非官方背书
AI DEEP REVIEW
AI 深度评测
7.2/10Consider
Ambitious Obsidian-backed agent memory with strong test fixtures, but install steps are undocumented and claims are hard
Code quality8
README cites CI badge, pytest suites, and reproducible fixtures (clone_25, lock_vs_neighbor) with explicit invariants, indicating real engineering rigor.
Security6
No install command or permission details are given, so risk from download-and-execute or secret handling cannot be assessed; neutral score.
Utility8
Addresses a genuine pain point (persistent cross-agent memory via Obsidian) with a concrete seal/distill/promote/lock workflow, though value depends on the user's vault.
Maintenance8
Last updated 2026-09-12, not archived, MIT licensed, and README references dated 2026-08-21 field data, suggesting active development.
Docs6
README is dense and jargon-heavy with no install command and heavy reliance on linked docs (VERIFY.md, PROTOCOL.md), making onboarding unclear for a new user.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
PROJECT README项目说明展开Collapse
正在读取 GitHub README...
README 暂时无法读取。
前往仓库PROJECT TOPICS
项目标签
VALIDATION LADDER
验证进度
01市场发现Passed
02归类识别Passed
03结构检查Pending
04实机验证Pending
FAQ
Frequently Asked Questions
What is DSH-KRouter used for?
Second brain for coding agents. Seal the day, distill into Obsidian, hit that page tomorrow. Cursor, Codex, Claude Code, DeepSeek Harness.
How popular is DSH-KRouter?
DSH-KRouter has 38 stars and 1 forks on GitHub, last updated 2026-09-12.
What license does DSH-KRouter use?
DSH-KRouter is distributed under the MIT license.
Is DSH-KRouter compatible with DeepSeek Harness?
DSH-KRouter is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
/10类依据
项目类型插件
功能/10类Agent 与会话
规则置信度Medium
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:No valid category tags。
Agent 与会话技能
MemOS
MemTensor
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
待结构检查
agentagentic-aiaiai-agents
Agent 与会话技能
memsearch
zilliztech
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
待结构检查
agentagent-memoryai-agentsclaude-code
Agent 与会话插件
harnessrouter
HarnessRouter
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
待结构检查
agent-apiagent-frameworkagent-harnessai-agents
Agent 与会话插件
Tianshu-harness
huiliyi37
Tianshu is a terminal coding agent runtime built on the harness project (Tui X Gui), with prefix-cache engineering optimization for DeepSeek V4 (measured steady-state hit rate of 97–99% in long sessions) and deep adaptation. It breaks out of the traditional AI coding assistant's limit of treating the LLM merely as a tool, and is built on a cognitive virtual machine (CVM), a self-awareness layer and Stigmergy self-decaying memory, making the AI a development partner with independent judgment and cognitive safeguards.
待结构检查
ai-agentcoding-agentcontext-managementdeepseek
Agent 与会话插件
graph-memory
adoresever
Deepseek Harness, Openclaw knowledge graph memory plugin. Invited to present at Tsinghua University seminar in April 2026. Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse
待结构检查
claude-codecodexdeepseekdeepseek-harness