Plugins
The complete directory supports discovery. Quality dimensions are shown separately; automated analysis does not prove feature completeness. The plugin manager continues local inspection.
Found 2155 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence
dsh-memoryqwert702/dsh-memoryCatalog AnalyzedProject+global long-term memory for the dsh web GUI: split POST /items endpoints, tool-call context merged into memory items as compact summaries, with deduplication and session-scoped persistence.MemoryGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-session-managerdream12347/dsh-session-managerCatalog AnalyzedDSH session manager: delete with trash/restore/purge, restore archived sessions, recent-activity stats, continue/pause, open log folder, unread markers, fork into a new chat, workspace grouping and sorting, context compaction threshold.Sessions & MessagesGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-anchor@yeastcloud/dsh-anchorCatalog AnalyzedSession instruction anchor for DeepSeek Harness: the first step of a new session injects a freely composed instruction block as a plugin-sourced message, and it is re-anchored after a summarizing compaction, every N turns, or when metered context pressure crosses a threshold. An /anchor command re-anchors on demand without a model call; a settings page manages the paged preset library, injection order, re-anchor source and character limits.Sessions & MessagesnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifact0.11.0dsh-context-budgetzpis666/dsh-context-budgetCatalog AnalyzedAdds per-route context window and compaction threshold fields to the Models settings page and a vendor-aware thinking-effort picker to the composer, writing llm-pi-ai capacities, reasoningEfforts, and a compaction-basic patch row.Models & ProvidersGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-trilogyTodayJin/dsh-trilogyCatalog AnalyzedPer-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.MemoryGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-file-memoryICCuse/dsh-file-memoryCatalog AnalyzedFile-backed working memory: memorize/recall key premises verbatim in a session notes file so they survive context compaction losslessly.MemoryGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-memory-nexusFrank-NF/dsh-memory-nexusCatalog AnalyzedIntegrated memory and context management plugin: four-layer memory system (L2-L4), context compression/trimming/freezing, prompt orchestration, input box UI buttons, and enterprise security with role-based access control.MemoryGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-hermes-memory@lcthe/dsh-hermes-memoryCatalog AnalyzedScoped persistent memory for DSH: memory_save/search/replace/remove/list across global, user, project and failure scopes, DSH storage-domain persistence with secret and prompt-injection scanning, session-scope search, retention cleanup, and optional session-start injection; standing context via memory_pin/memory_pins/memory_unpin.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifact0.2.2auto-compactauto-compactCatalog Analyzed会话级自动上下文压缩Plugin：回合中每步前 + 回合结束检测上下文用量，超过会话阈值自动 compact，摘要注入上下文后自然继续（DeepSeek Harness / DSH）MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.3.0dsh-context-compactorkusesad-1122/dsh-context-compactorCatalog AnalyzedDSH 上下文压缩/总结Plugin：80% 自动全局详细总结压缩（保留核心任务/决策/待解决问题/重要文件位置，删除调试细节与已解决错误），压缩后验保证 totalTokens 必须真实下降，context-overflow 自动恢复，/compact + /context-status，输入框上方一键按钮MemoryGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-smart-compactLiangebra/dsh-smart-compactCatalog AnalyzedDeepSeek Harness 智能上下文压缩引擎（CompactionEngine 后端）：可配置阈值提示、强制自动压缩Security网、DCP 风格去重/清理建议、自定义摘要提示词。零外部Status，原文永不删除。Smart context compaction engine for DeepSeek HarnessMemoryGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-observational-memoryEPCN-fla/dsh-observational-memoryCatalog AnalyzedDistills session work into background observations and reflections to preserve context across compaction.MemoryGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-memory@hr98w/dsh-memoryCatalog AnalyzedClaude Code-inspired Auto Memory meets Codex-inspired Session consolidation, bringing simple, transparent, and context-efficient long-term memory to DeepSeek Harness.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.4dsh-auto-memory@a9i5k4/dsh-auto-memoryCatalog AnalyzedProactive associative memory for DSH: zero-prompt recall injected at a fixed boundary, three-layer auto-consolidation, skill crystallization, and Astra-style context management - handoff ledgers and a PLAN whiteboard that survive context-window switches, water-level sensing with an auto-detected model window. Local Markdown storage, model-agnostic, zero deps; lexical 0GB floor with optional semantic tiers.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit2 reported in bounded auditArtifact3.0.0dsh-memorydsh-git-memoryCatalog AnalyzedLocal Git-backed long-term memory for DeepSeek Harness with hybrid CJK/English retrieval, cited context, transactional sync, previews, and rollback.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.8.1dsh-simple-wiki-memorydsh-simple-wiki-memoryCatalog AnalyzedA super-simplified LLM-wiki memory plugin: one index document (auto-loaded) + one markdown file per topic (read only when needed) — no dumping everything into the context and burning tokens. Simple and lightweight, painless to install/uninstall, and freely editable however you like.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.3dsh-context-compression-improveddsh-context-compression-improvedCatalog AnalyzedSame-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.Sessions & MessagesnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1OpenViking#examples/dsh-memory-plugin@openviking/dsh-memory-pluginCatalog AnalyzedOpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.2Source candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation