Discover The Best DSH plugins
1202results
Find plugins for conversation memory, knowledge retrieval and context management.
@detpecca/dsh-llm-wikiDeepSeek Harness plugin — manage an LLM-Wiki knowledge base from the agent: wiki_search / wiki_read / wiki_stats / wiki_validate / wiki_errorbook / wiki_ingest
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:detpecca/dsh-llm-wiki@djasdh/interest-memoryCross-session long-term memory for AI agents — local Go service (~50MB RAM, SQLite-vec, verify-augmented) with bridges for DeepSeek Harness, Claude Code, Codex, Hermes, OpenClaw, opencode, pi, Reasonix.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:djasdh/interest-memory@dsh-enhanced/memory-wiki-bridgeProposal-only, provenance-stable promotion between DSH personal Memory and Wiki.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:22-ai-00/dsh-enhanced#d5a223edf3d73b0297a36b3e10f8d24142f94153&path:plugins/memory-wiki-bridge@dsh-enhanced/personal-assistantA core-only meta-bundle for the DSH personal assistant policy, memory, Wiki, and automations plugins.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:22-ai-00/dsh-enhanced#d5a223edf3d73b0297a36b3e10f8d24142f94153&path:plugins/personal-assistant@dsh-enhanced/personal-memoryScoped, bounded, approval-gated long-term memory for DeepSeek Harness agents.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:22-ai-00/dsh-enhanced#d5a223edf3d73b0297a36b3e10f8d24142f94153&path:plugins/personal-memory@dsh-enhanced/personal-wikiA safe, searchable, approval-gated Markdown knowledge vault for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:22-ai-00/dsh-enhanced#d5a223edf3d73b0297a36b3e10f8d24142f94153&path:plugins/personal-wiki@dsh-external/dsh-ocr1-memory基于 DeepSeek-OCR1 光学压缩记忆系统：把记忆渲染为图像存储，支持 SoM 分段、年龄衰减/模糊化、激活召回、DSH Agent 检索
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DDDFXYqiming/dsh-ocr1-memory@dsh-memory/consolidateCLS-style replay consolidation pass with LLM summarizer and deterministic fallback
@dsh-memory/emit-contextMneme context backend: compile state and recall evidence into agent context at session start and pre-step
@dsh-memory/emit-skillMneme skill backend: lower active policy nodes into the DSH skill registry
@dsh-memory/emit-toolMneme tool backend: memory_remember/recall/list/forget/trace model tools
@dsh-memory/extractRecMem-gated LLM claim extraction pass with replay-logged raw output
@dsh-memory/fdoFeedback-directed optimization: recall/confirm signals update salience and retrieval weights
@dsh-memory/index-graphGraph candidate index over claim/relation facts with PPR-style spreading activation
@dsh-memory/index-replayMneme replay search backend: sessionQuery FTS hits mapped back to ledger nodes with literal fallback
@dsh-memory/index-vectorVector candidate index as a disposable projection cache with deterministic fallback
@dsh-memory/irMneme memory intermediate representation, ctx.memory engine, and pure compiler folds
@dsh-memory/layersMemGPT-style layered allocation policy
@dsh-memory/linksA-MEM-style note linking: shared subjects become relation nodes
@dsh-memory/lowerMneme front-end pass: lower DSH session events into typed memory IR nodes
@dsh-memory/optimizeMneme optimize pass: TTL forgetting, contiguous-run consolidation, and catalog budget
@dsh-memory/projectionsSession projection pass: memory/catalog and memory/stats over DSH sessionProjections
@dsh-memory/solveMneme solve pass: version resolution, evidence conditions, and activation analysis
@kakadeka/dsh-batonBaton 项目接力协作系统 —— DeepSeek Harness 组合包（19 个 baton_* 工具）
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kakadeka/BatonUse a feature keyword or category, then sort by recent updates or GitHub stars.
Read the description, AI analysis and original README to understand what a plugin does.
Review compatibility, dependency ranges and instructions, then copy the available install command.
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.