small-model-harness

iknowkungfubar/small-model-harness

★ 0 stars Python AI/LLM Updated 1d ago

Defensive harness for 1B-12B local LLMs in production agentic workflows. 5-layer architecture: routing, validation, constraint, circuit break, context management. Hermes plugin + MCP server.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

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

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "small-model-harness": {
      "command": "uvx",
      "args": [
        "small-model-harness"
      ]
    }
  }
}

Or install with pip: pip install small-model-harness

README Excerpt

**Defensive harness for running 1B–12B parameter models in production agentic workflows.** Five-layer architecture: routing → validation → constraint → circuit break → context management. Delivered as a Hermes plugin (deterministic enforcement) + MCP server (analysis tools). Small models (1B–12B) have dramatically closed the quality gap with frontier models, but the **reliability gap persists**:

Tools (5)

harness_classify_taskharness_compactharness_context_statusharness_resetharness_route

small-model-harness

Quick Install

README Excerpt

Tools (5)

Related AI/LLM Servers