Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "offload-harness": {
      "command": "go",
      "args": [
        "run",
        "github.com/dmmdea/offload-harness@latest"
      ]
    }
  }
}

README Excerpt

<div align="center"> **Delegate the grunt work to a free local model — keep your cloud tokens for judgment.** A local-first harness that offloads short-context, low-judgment work — **summarize · classify · extract · triage** (plus vision, OCR, transcription, and image/SVG generation) — to a free **Gemma-family cascade** served by [llama.cpp](https://github.com/ggml-org/llama.cpp). It runs as a Go CLI and as an **MCP server** for AI coding agents. It **never calls a cloud model**: when it can't d

Tools (20)

auto_healcache_pathclassify_min_confidencecompletion_pathconfidence_margin_thresholdendpointescalation_modelexemplar_shotsledger_pathmax_input_charsmax_retriesmodeloffload_assess_imageoffload_classifyoffload_extractoffload_extract_imageoffload_generate_audiooffload_generate_imageoffload_generate_svgoffload_generate_video

offload-harness

Quick Install

README Excerpt

Tools (20)

Related AI/LLM Servers