DSH-PLUGIN STORE / LIVE CATALOG

DSH插件商店

聚合 GitHub 上的 DSH 插件,打造 DeepSeek Harness 生态的一站式目录。

已收录
6553
功能分类
11
更新时间
10/07 02:01

33 个项目,匹配「context-engine」

Agent 与会话 插件

honcho

plastic-labs

Memory library for building stateful agents

agent-memory agentic-rag ai ai-agents
Agent 与会话 技能

Vibe-Skills

foryourhealth111-pixel

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

agent-framework agent-skills agentic-coding ai-agents
安全与治理 技能

ANOLISA

agentic-os-org

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

agent-infrastructure agent-memory agent-runtime agent-security
文件与数据 插件

thoughtdag

chenxiachan

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

agentic-search ai-tools context-engineering cordis-plugin
Agent 与会话 完整应用

dsh-auto-memory

AskTheWay

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.

agent-harness agent-memory ai-agent ai-tools
Agent 与会话 完整应用

agent-context-editor

jermaine123123

Cross-agent plugin for manually excluding and editing AI conversation context, with search, filtering, hide/restore, undo, and original Session preservation.

agent-tools ai-agent ai-agents coding-agent
开发工具 技能

hedgehog

skyf0xx

HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven, BMAD-METHOD plan, so Claude Code, Cursor & Gemini CLI stay locked to it. A CLI-enforced state machine for agentic coding. Now builds DeepSeek DSH Plugins. DeepSeek Harness、DSH 插件、AI 编程、BMAD 方法. AI Copywriting

agent-skills agentic-coding ai-agents ai-assisted-development
开发工具 插件

leantoken

morluto

Code intelligence for agents: find the code that matters and keep your context window and tokens lean.

ai-coding code-intelligence code-navigation code-retrieval
Agent 与会话 技能

agent-handoff-skill

WeirdSky924

Use this cross-platform skill in Codex or Claude Code to establish repository-local continuity memory so a future agent can recover objective, status, decisions, validation, risks, and next actions without relying on previous chat history.

agent-handoff agent-skills claude-code codex
Agent 与会话 插件

dsh-layered-memory

JunNanLYS

让 DeepSeek Harness 拥有跨会话长期记忆:AI 自动记住你是谁、你的项目和偏好,新会话直接带上背景,生活与工作记忆自动分开互不干扰,零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers who you are, your projects and preferences across sessions, keeps personal and work memories separate, zero-config.

agent-memory ai-agent context-engineering cordis-plugin
Agent 与会话 插件

GraphFlow

Roarpeng

Local-first code knowledge graph and context harness for coding agents. MCP + DeepSeek Harness (dsh) plugin.

context-engine cordis cordis-plugin deepseek-harness
Agent 与会话 插件

agent-body

1420079678-ctrl

Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command, reflex arcs fire with zero model calls, memory consolidates while idle, every failure is attributed before retry. Reproducible offline, MIT.

agent-framework agent-plugins ai-agents ai-memory
开发工具 插件

toolshrink

unclecode

Cut large agent tool output by what it means, not by where it was cut. 13 content-aware reducers + DeepSeek Harness plugin.

ai-agents claude-code context-engineering deepseek-harness
模型与 MCP 插件

dsh-mcp-lens

labmimors

Search 1,000 MCP tools through two interfaces in DeepSeek Harness. Load exact schemas on demand and keep structured results usable across tool calls.

agent-harness context-engineering context-optimization context-reduction
部署运维 基础设施

dsh-fast

PerryLink

Read-only performance diagnostics for DeepSeek Harness: session load/restore timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via /fast, persisted as reconstructable session events with async sampling off the model path.

ai-agent ai-agents context-engineering cordis
开发工具 插件

gatherthread

TH060419

GatherThread 共序:本地 AI 编程 Agent 多人联机协作、实时共享上下文。Self-hostable collaboration for local AI coding agents, Codex Desktop connector & DeepSeek Harness plugin.

agentic-coding ai-agents coding-agents collaboration-platform
Agent 与会话 插件

AgentNavi

CoaseEdge

The navigation of AI Agent.

agent-memory ai-agent claude-code codex
文件与数据 技能

Memory and token-optimization plugin toolkit for DeepSeek Harness: cross-session knowledge graph memory + five-layer token-saving orchestration.

agent-memory agent-skill ai-agents context-engineering
Agent 与会话 插件

守藏 Shoucang — DeepSeek Harness (DSH) 长期记忆插件:会话蒸馏自动沉淀 × 深度睡眠反思归纳 × 词法+向量混合召回 × 认知环引导 × 主动遗忘,配本地设置面板。一条命令装上,助理即拥有跨会话记忆——数据全在本机,零上传。

agent agent-memory ai-assistant ai-memory
Agent 与会话 插件

Long-term memory for AI agents on Jev. Keep raw records, judge them with a fast System 1 model and answer from under 4k tokens of context.

agent-memory ai-agents context-engineering deepseek-harness
Agent 与会话 插件

DeepSeek Harness 的 AdaptiveContextPlane (ACP) 插件——带治理的长期记忆系统

adaptive-context ai-agent context-engineering deepseek-harness
开发工具 插件

dsh-graft-plugin

adithyanraj03

A DeepSeek Harness plugin that puts graft — a prebuilt graph of every symbol, its file:line span, and who calls what — in front of both you and the model.

ai-agents code-graph code-indexing code-intelligence
开发工具 插件

superself

fxylabs

The open Company State Runtime — version control for your project's state. Goals, decisions, work, and evidence outlive every chat, context window, and agent session. Ships the self CLI.

agent-memory agents ai ai-agents
模型与 MCP 插件

ast-mcp-server

yailPeralta

Correctness-oriented MCP server and batch CLI for compact structural reads and reviewed TypeScript/JavaScript edits.

ast codebase-indexing codebase-intelligence context-engineering