dsh-local-llm-connect
Connects actively running local LLMs from llama.cpp and NInfer managers into DeepSeek Harness.
Install
$ dsh plugin --profile desktop add dsh-local-llm-connectPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Discovers local LLM manager models and control endpoints automatically
- Dynamically registers running models and removes stopped ones every 15 seconds
- Supports dual inference engines: Windows-native llama.cpp and WSL-hosted NInfer
- Provides manual instant refresh and status monitoring in DSH settings UI
- Accurately performs engine-specific readiness checks and vision capability mapping
Useful For
- Using local GGUF models served via llama.cpp inside DeepSeek Harness
- Integrating WSL-based NInfer single-file models into Harness workflows
- Keeping DSH model selection list in sync with locally running instances without manual endpoint setup
Who It Fits
- Developers running local LLMs with llama.cpp or NInfer
- DeepSeek Harness users requiring offline or locally hosted model providers
Documented Limitations
- Requires the local llm-manager (v1.3.0 or higher) control service to be running to discover models
- Stopping a model mid-conversation causes subsequent prompts in that thread to fail after provider deregistration
- Requires Node.js ^22.19.0 or >=24.0.0
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 6 development, 7 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- ClearLeaf13/dsh-local-llm-connect
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 6082444 · 2026-09-27
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-27
- Last release
- 2026-09-24
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Command Code LLM provider bundle for DeepSeek Harness with model catalog, quota tracking, and multi-account rotation.
View plugin →Multi-account failover model pool, quota aggregator, and automation suite for DeepSeek Harness.
View plugin →Free frontier LLM provider plugin for DeepSeek Harness with upstream probing and local OpenAI-compatible gateway.
View plugin →Use ChatGPT, Claude, Grok, GitHub Copilot, and Antigravity subscriptions as DeepSeek Harness LLM providers via OAuth.
View plugin →