dsh-local-ai
Local-model (Ollama & OpenAI-compatible) integration and task-based routing with automatic cloud fallback for DeepSeek Harness.
Install
$ dsh plugin --profile web add "github:PerryLink/dsh-local-ai#main"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.
Key Capabilities
- Manage Ollama models with dedicated tools (ollama_list, ollama_show, ollama_pull, ollama_remove)
- Registers Ollama and OpenAI-compatible provider endpoints via ctx.llm LlmAdapter
- Rule-based request routing by task purpose (e.g. compaction, session title), keywords, or default
- Automatic cloud fallback if local routing fails before token generation
- Process and API health checks alongside a one-shot /ollama status command
- Support for vision payloads when reported by local models
Useful For
- Routing privacy-sensitive or offline prompts to local models while keeping general queries on cloud LLMs
- Offloading background housekeeping tasks like session title generation or context compaction to lightweight local models
- Inspecting and downloading Ollama models directly within DeepSeek Harness sessions
Who It Fits
- DeepSeek Harness developers seeking offline or privacy-centric local model execution
- Users running Ollama, LM Studio, vLLM, or llama.cpp locally alongside cloud LLMs
Documented Limitations
- Requires a running Ollama or compatible local inference server
- Fallback to cloud only succeeds if the local route fails before emitting the first token; mid-stream failures are forwarded directly
- Developed and tested against DeepSeek Harness 0.1.1-rc.2
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.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- PerryLink/dsh-local-ai
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 3b48d9e · 2026-09-15
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
- 12GitHub stars
- Forks
- 1
- Open issues
- 0
- Last commit
- 2026-09-12
- Last release
- 2026-09-12
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Compatibility bridge and host ABI enabling unmodified Pi plugins to run natively on DeepSeek Harness.
View plugin →Composable three-tier memory control plane for DeepSeek Harness with runtime context, searchable documents, and pluggable long-term memory.
View plugin →Preview, create, and edit spreadsheets, docs, slides, and canvases in DeepSeek Harness powered by Univer.
View plugin →