modelspoke
Local OpenAI-compatible model server discovery and reasoning metadata resolution plugin for DeepSeek Harness.
Install
$ dsh plugin --profile web add modelspokePlugin 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 OpenAI-compatible model endpoints and capabilities automatically
- Offers first-class support and extended capability discovery for llama-swap and Ollama
- Provides built-in capability presets for common base models on endpoints like vLLM, sglang, and llama-server
- Enables configurable reasoning effort level mappings from UI settings to model parameters
- Detects and configures image input and multimodal capabilities for supported local models
- Integrates a settings card directly into the DeepSeek Harness web interface for profile and model curation
Useful For
- Connecting DeepSeek Harness to locally hosted LLM servers without manual YAML configuration
- Configuring reasoning and thinking effort levels for local reasoning models
- Curating which local models are accessible to the agent and tuning context window/token limits per model
- Integrating multimodal vision-capable local models into DeepSeek Harness workflows
Who It Fits
- Developers running local LLMs with Ollama, llama-swap, vLLM, or llama.cpp
- DeepSeek Harness users requiring granular control over local model capabilities and reasoning effort
- Self-hosted AI enthusiasts seeking a GUI-based provider setup in DSH
Documented Limitations
- Requires DeepSeek Harness 0.1.7 or newer with pnpm and the dsh plugin command installed
- Deep template-contract fields (compat) still require manual file editing rather than web UI modification
- End-to-end model discovery quality depends on the capability metadata exposed by the underlying model server
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, 18 development, 4 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
- americanjeff/modelspoke
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- e32b4ba · 2026-10-25
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
- 2026-10-18
- Last release
- 2026-10-18
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 →Use ChatGPT, Claude, Grok, GitHub Copilot, and Antigravity subscriptions as DeepSeek Harness LLM providers via OAuth.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Vision routing and pixel-level tools for text-only DeepSeek Harness agents with built-in free fallback.
View plugin →