Agent 与会话
插件
DeepSeek Harness (DSH) local-first cross-session project memory: zero bundled runtime deps, bounded cache-friendly Hot Memory, BM25 recall/cache, provenance, lifecycle and bilingual Web GUI; no embeddings or external service. / DSH 本地项目记忆插件。
agent-memory
ai-agent
bm25
cache-aware
Agent 与会话
技能
DeepSeek Harness (DSH) 记忆插件全家桶：中文可用会话全文检索（FTS5 trigram）、工具结果去重、混合向量+FTS5 记忆检索、跨会话核心记忆、近无损压缩、技能管理器+后台自我进化，以及模型写不到的用户专属层（手写或被固定的技能与记忆，模型工具与后台进化一律改不动）。86 单测；支持 DSH 0.1.5-rc.3 ~ 0.2.x
agent-skills
ai-agent
chinese-search
cjk
文件与数据
插件
A reproducible science workbench plugin for the DeepSeek Harness: agent-driven cells, inline figures with feedback/rerun, manifest provenance, and environment snapshots. 9 bio_* tools + workbench UI + publication-grade figure skills.
agent
bioinformatics
deepseek-harness
dsh-plugin
Agent 与会话
基础设施
Evidence-backed, explainable multi-model routing for DeepSeek Harness — policy resolution, provenance, and compatibility boundaries.
agent-distribution
agent-orchestration
ai-agent
coding-agent
安全与治理
插件
Risk-aware approval layer for high-risk AI Agent tool calls
agent-security
dsh-plugin
provenance
tool-security
Agent 与会话
插件
TMCRA Core — local-first, scope-isolated long-term memory runtime for AI agents.
agent-memory
ai-agents
claude-code
codex-plugin
模型与 MCP
技能
Content-addressed receipts for skills actually loaded by DeepSeek Harness
agent-skills
ai-agent
capability
deepseek-harness
文件与数据
插件
Content-addressed artifact, fact, action and report lineage for DeepSeek Harness
ai-agent
content-addressed-storage
data-lineage
deepseek-harness
部署运维
基础设施
洞察 — read-only insight panel for a DeepSeek Harness profile: where every plugin, service, tool and model came from, which config layer inserted or disabled it, and what is running right now.
configuration
cordis
deepseek-harness
devtools
部署运维
基础设施
Observe-only provenance ledger over public DeepSeek Harness runtime evidence
deepseek-harness
dsh-plugin
observability
privacy
Agent 与会话
插件
User-governed local memory spaces for DeepSeek Harness — explicitly share selected sessions with previewable, versioned, provenance-aware recall.
agent-memory
ai-agent
deepseek-harness
dsh-plugin
Agent 与会话
插件
Long-term memory for DeepSeek Harness in Claude Code's format: private, overlay, or shared with Claude Code, with provenance on every file
claude-code
deepseek-harness
deepseek-harness-plugin
dsh
学习研究
技能
Fact-checking skill for DeepSeek Harness: multi-source verification against the open web, domestic and international ecosystems, optional TypeSafe Jev (System One) judgements.
cordis-plugin
deepseek-harness
deepseek-harness-plugin
dsh
文件与数据
插件
LLM Wiki workbench for dsh-better-sidebar: browse and lint a Karpathy-style interlinked markdown wiki, open pages with the native markdown viewer, clickable [[wikilinks]] and provenance/relative .md links, and backlinks. Ships the llm-wiki agent skill.
dsh
dsh-plugin
knowledge-base
markdown
其他
基础设施
Mod-style plugin management for DeepSeek Harness: provenance, preview-first hot toggles, presets, AI filtering, diagnostics, and updates.
cordis
deepseek-harness
dsh
dsh-plugin
Agent 与会话
插件
Self-evolving memory for DeepSeek Harness: capture → dream consolidation → retrieval injection → evolve. User profile, project memory, correction learning, resume narrative — with provenance back to the replayable session log. 自进化记忆插件。
ai-agent
deepseek-harness
dsh-plugin
memory
安全与治理
技能
DSH plugin: lock, verify and govern AI agent skills. Tells you what a skill can do before you install it — and when it silently gains a capability after your review. Ships no boot-time code.
agent-skills
ai-agents
ai-security
devsecops
模型与 MCP
插件
Deliverable evidence-chain & conformance checks for DSH — turn requirements into an executable spec, trace every number to a provenance ledger, audit PDF/OOXML metadata and archive manifests. MCP-ready.
conformance
deepseek-harness
dsh-plugin
lint
界面增强
插件
DSH 插件：Jupyter 式活体运行本——回合可回放的数据流 DAG，含 git 提交出处节点、子 agent 交接边、持久账本、悬停重跑与 LLM 解释
agent-observability
dag
data-lineage
dataflow
文件与数据
插件
A safe, bounded, read-only perception layer for AI agents to observe administrator-defined JSON APIs.
ai-agent
deepseek-harness
dsh-plugin
json-api
