← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-koboldcpp-hands

DeepSeek Harness tool plugin that delegates text tasks and vision/OCR work to a local KoboldCpp server.

VisionTerminal & TUIDeveloper ToolsSecurity & Policy
0GitHub Stars0ForksUpdated2026-08-21

Install

No clear install command was found in the current repository evidence.

Plugin 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.

source-grounded
dsh-koboldcpp-hands adds two agent-callable tools to DeepSeek Harness for non-streaming text and multimodal requests against a local KoboldCpp OpenAI-compatible server. It can launch and manage a configured KoboldCpp process or reuse an existing server.

Key Capabilities

  • Registers `koboldcpp_run` for local text generation tasks such as rewriting, extraction, translation, and summarization.
  • Registers `koboldcpp_vision` for image analysis, OCR, and multi-image comparison.
  • Accepts vision images from local paths, data or HTTP(S) URLs, and, when supported by the selected main model, conversation attachments.
  • Launches KoboldCpp on demand using a user-provided executable and `.kcpps` configuration, performs health checks, and supports idle, exit, or never-stop behavior.
  • Reuses externally started KoboldCpp servers without stopping them.
  • Supports live configuration overrides through Harness settings and executable/config environment-variable fallbacks.

Useful For

  • Offload repetitive text transformations to a local GGUF model.
  • Perform local OCR or image analysis with a multimodal KoboldCpp model and `mmproj`.
  • Compare two to four images in one vision request.
  • Use a locally hosted model as an agent tool while retaining an online main conversation model.

Who It Fits

  • DeepSeek Harness users running KoboldCpp locally.
  • Users with local GGUF text or multimodal models.
  • Agents and workflows needing local text processing, OCR, or image comparison tools.

Documented Limitations

  • Requires Node.js 20 or later, DeepSeek Harness, a KoboldCpp binary exposing `/v1/chat/completions`, and user-supplied model files.
  • The plugin does not provide an LLM provider replacement, streaming responses, GPU/backend detection, model files, or API-key authentication.
  • Vision requires a multimodal GGUF model plus an `mmproj` configured in the user’s `.kcpps` file.
  • With a text-only main model, conversation attachments are unavailable to the vision tool; use explicit local paths or URLs instead.
  • Its documented compatibility target is the DeepSeek Harness `0.1.0-rc` series, tested against `0.1.0-rc.7`.

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Not Found

No root package.json was captured in the latest GitHub snapshot.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
MicroHEROX/dsh-koboldcpp-hands
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
0e75b23 · 2026-09-12

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
2026-08-21
Last release
2026-08-15
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app