SEMANTIC DIRECTORY · plugin-directory-semantic-v3-18

Local Inference Operations

在本机部署和管理模型推理服务,包括 Ollama、llama.cpp、vLLM 等服务启停、GPU 与显存检测、GGUF 或量化参数、吞吐测量和本地任务卸载;不包含远程提供商账号接入。

Use keyword search
Source catalog discovery.composite.2026-09-06.v1-0-5.b92b985e31dfCanonical structure · 823 nodes · 14829 plugins

Leaf membership

15 plugins

dsh-JEPA-adapterhuermi/dsh-JEPA-adapterCatalog Analyzed适配调用JEPA模型的Plugin,提供一个本地的JEPA模型项目(需要进一步训练持续学习,已完成基本工具调用),可在家用计算机配置上运行。A plugin adapted to call the JEPA model, providing a local JEPA model project (requires further training for continual learning; basic tool calling has been completed) that can run on a home computer CPU.UI EnhancementsGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-koboldcpp-handsdsh-koboldcpp-handsCatalog AnalyzedHands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle management.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifact0.1.1Evidence updated2026-09-07Public signals1 stars · 817 downloadsdsh-llamacppjwilson411/dsh-llamacppCatalog AnalyzedDeepSeek Harness LLM adapter for a local llama.cpp OpenAI-compatible server.Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-llm-mlxrobbywang25/dsh-llm-mlxCatalog AnalyzedUse local MLX-LM or MLX-VLM models in DeepSeek Harness through a loopback OpenAI-compatible provider, with optional DSH-owned server startup.Models & ProvidersGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-local-aidsh-local-aiCatalog AnalyzedOllama provider for DeepSeek Harness with model management, health checks, rule-based local routing, and cloud fallback.Models & ProvidersnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.2.4Evidence updated2026-09-07Public signals6 stars · 1926 downloadsdsh-local-llmwertyBSd/dsh-local-llmCatalog AnalyzedLocal LLM integration plugin for DeepSeek HarnessTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-local-llm-controllerLbunc/dsh-local-llm-controllerCatalog Analyzed为DSH接入本地大模型能力:在「设置→Plugin」页一键启停本地 llama.cpp 大模型(双槽x双模态x双预设),卡片内配置、一条命令安装、自动注册,装完即用| Enable local large model capabilities for DSH: One-click start/stop for local llama.cpp models (dual‑slot × dual‑modal × dual‑preset) right in Settings → Plugins; configure within the card, install with a single command, automatically register, and ready to useTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-local-modelsVmarcelo49/dsh-local-modelsCatalog AnalyzedUse local models via Llama.cpp on your deepseek harnessTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-local-perfflowingboy/dsh-local-perfCatalog AnalyzedDurable DeepSeek Harness bundle: local-model performance tuning as a re-installable plugin layer (compaction, tool-result pruning, time context, cloud title routing, text-toolcall guard) — survives dsh updatesMemoryGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-mlx-localJshGao/dsh-mlx-localCatalog AnalyzedDSH plugin from JshGao/dsh-mlx-localTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-model-managerAnsonfishing/dsh-model-managerCatalog AnalyzedControl panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM validation, GPU detection, and tok/s benchmarks.Models & ProvidersGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-wsl-hostsvc173787247/dsh-wsl-hostsvcCatalog AnalyzedProbes Windows-host Ollama, LM Studio, vLLM, and llama-server from WSL and suggests a baseURL.WSL & Windows InteropGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starslocal-dshliangchen-harold/local-dshCatalog AnalyzedDSH plugin from liangchen-harold/local-dshTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsMult-Hands-Eyes-MCPMicroHEROX/Mult-Hands-Eyes-MCPCatalog AnalyzedMCP server that gives online LLMs local hands and eyes: OpenAI-compatible local inference (KoboldCpp / Unsloth / llama.cpp / LM Studio / Ollama) for cheap text work and vision work (OCR / image analysis / comparison).Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsrapid-mlx-dsh-providerraullenchai/rapid-mlx-dsh-providerCatalog AnalyzedNative Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals71 stars

Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.