Hamjamiyat
LLM Eval Harness
io.github.razilzul/llm-eval-harness
Run a golden set and gate LLM model swaps on accuracy, with latency and cost per request.
Tavsif asl tilda
Ulash
Konfiguratsiyani mijoz sozlamalariga qo'shing. <Burchak qavslar> ichidagi qiymatlarni o'zingiznikiga almashtiring.
claude_desktop_config.json
{
"mcpServers": {
"llm-eval-harness": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ANTHROPIC_API_KEY",
"-e",
"GEMINI_API_KEY",
"ghcr.io/razilzul/llm-eval-harness:1.0.0"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}Ma'lumotlar
- Nomi
- io.github.razilzul/llm-eval-harness
- Versiya
- 1.0.0
- Yangilangan
- 18-okt, 2026
- Manba
- Rasmiy MCP Registry
- Repozitoriy
- https://github.com/razilzul/llm-eval-harness