@dshserver/runtime-gatewayManaged per-user Runtime Gateway for DeepSeek Harness
최고의 DSH 플러그인을 만나보세요
7257개 결과
에이전트 구성, 다중 Agent 협업 및 작업 실행 플러그인을 찾아보세요.
@dshserver/runtime-gatewayManaged per-user Runtime Gateway for DeepSeek Harness
@dshworks/dsh-crewRun Claude Code and Codex as live terminal panes beside dsh: a split view in the web UI, buttons to seat them, and tools that let the dsh agent hand them work and read their screens.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dshworks/dsh-crew@dshx/dshxClaude Code / opencode-style terminal coding agent on deepseek-harness + dsh-TUI with a built-in prefab-anchored-standard preset
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NoNshiranai/dshX@elinpf/dsh-opsSingle-package deployment unit for the dsh-ops plugin suite: host-plane rows plus the ops agent preset, over the granular @elinpf/dsh-ops-* packages.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Elinpf/dsh-ops-plugins#64b1d76649bf24155173c74254d0fb61d12815d5&path:packages/ops@elinpf/dsh-ops-access-gateOps access gate — per-session credential brokering. Owns an in-process grant ledger keyed by agent.id and registers a pure-decision broker (ro/rw) into the ops-access seam. Never touches credential fields.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Elinpf/dsh-ops-plugins#64b1d76649bf24155173c74254d0fb61d12815d5&path:packages/ops-access/gate@elinpf/dsh-ops-access-uiBrowser half carrier for @-mentioning ops-access profiles: the host row exists only for client-bundle discovery; candidates come from GET /ops-access/list served by @elinpf/dsh-ops-access, and mention expansion (agent/pre-step) lives there too.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Elinpf/dsh-ops-plugins#64b1d76649bf24155173c74254d0fb61d12815d5&path:packages/ops-access-ui@elves-ai/dsh-web-search-firecrawlFirecrawl-backed search provider for the DeepSeek Harness web capability seam (ctx.web)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:elves-ai/dsh-web-search-firecrawl@ericjiang0423/dsh-orchestratorLocal-first issue board for DeepSeek Harness: board data, model-facing tools, an agent planning loop, and a human approval queue for agent-proposed issues.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EricJiang0423/dsh-orchestrator@falling-ts/dsh-force-compactDSH Cordis plugin: hooks the core model-request seam (agent/pre-step + agent/request) to force-compact a session's context and disable thinking per the "强制压缩配置" settings namespace (disableThinking, autoThresholdTokens, retainLatestTokens, turnEndForceCompactionEnabled). When the threshold fires (or /force-compact queues while busy), the latest `retainLatestTokens` of the conversation's surface tokens are KEPT VERBATIM and everything before that cutoff is COMPACTED INTO A SINGLE SUMMARY NODE in one LLM call (original span entries become shadowed/skipped). Also compacts at each turn/end and at each session/flush durability checkpoint. Host half is a pure listener; a web client half registers a settings.section (强制压缩 / Force Compact) that reads and writes the same settings namespace.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:falling-ts/dsh-force-compact@fly3366/deepjitDeepJIT: JIT-compile repeated agent workflows into skills and flow templates for deepseek-harness (dsh)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:fly3366/DeepJIT@foliodrop/dsh-publishPublish agent-created content from DeepSeek Harness to a shareable FolioDrop URL.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jaxxchen003/foliodrop-dsh-publish@frog755/dsh-hybrid-memoryHybrid memory plugin for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md, read on demand, zero context cost) + L2 searchable knowledge base (one-fact-per-file, SQLite FTS5) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and approved Agent Hub documents. No automatic injection. Data lives on D drive, never C.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Frog755/dsh-hybrid-memory@gamegeek-saikel/dsh-archive-managerPermanent session deletion for the DSH Web GUI — remove a session's log, workspace accounting, archive/pin markers, projection-cache row, subagent children, and spill data from the sidebar row menu, while DSH's own archive UI keeps owning archived sessions.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Saikel-Orado-Liu/dsh-archive-manager@georesearch/dsh-agent-lifecycleGeoResearch-owned resume entry point with pre-publication identity checks
@georesearch/dsh-bundleManaged GeoResearch host-plane bundle for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:georesearch-dsh/georesearch-dsh#ff8a6556d382fe43639c67e5936f859fe3e7e63c&path:packages/bundle@georesearch/dsh-claim-serviceHost-assessed claims, user approval, and WritingPacket filtering for GeoResearch Phase 6
@georesearch/dsh-compat-rc5The only GeoResearch adapter allowed to touch DeepSeek Harness rc.5 APIs directly
@georesearch/dsh-contractsStable GeoResearch roles, installation records, digests, schemas, and error codes
@georesearch/dsh-delegation-toolsManaged one-shot GeoResearch delegation and specialist bootstrap tools
@georesearch/dsh-evidence-providersReplay-safe literature and PDF provider implementations for GeoResearch Phase 3
@georesearch/dsh-evidence-serviceCrash-safe literature, PDF, source, and evidence tools for GeoResearch Phase 3
@georesearch/dsh-experiment-serviceExperiment protocol lock, amendment, and authoritative result service for GeoResearch Phase 5
@georesearch/dsh-file-serviceSession-bound universal file intake and safe read tools for GeoResearch
@georesearch/dsh-geospatial-provider-pythonPersistent Python geospatial provider for GeoResearch Phase 5
기능 키워드나 카테고리로 범위를 좁히고 최근 업데이트 또는 GitHub Star로 정렬하세요.
소개, AI 분석, 원본 README를 읽고 플러그인의 기능을 확인하세요.
호환성과 의존성 범위, 설치 안내를 확인한 뒤 제공된 설치 명령을 복사하세요.
DeepSeek Harness 커뮤니티 플러그인 디렉터리입니다. 소개, 소스 링크, 설치 안내를 모아 확장 기능 검색과 비교를 돕습니다.
아니요. 상세 페이지는 기록된 호환성과 의존성 범위를 표시합니다. 알 수 없음은 호환을 의미하지 않으므로 설치 전 프로젝트 문서를 확인하세요.
상세 페이지의 설치 영역을 확인하세요. 명령이 있으면 Harness 환경에 복사해 실행하고, 없으면 프로젝트 README를 따르세요.