com.computesage/stackbench

up checked 2026-11-11T08:38:39.440Z

Unclaimed · Unverified

Publisher-provided title

ComputeSage StackBench

Publisher-provided description

GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.

Summary by lookupd

Provides GPU and LLM inference benchmark evidence, deployment fit checks, performance predictions, and vLLM or llama.cpp launch configs.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http stackbench https://mcp.computesage.com/mcp

Codex, remote (streamable-http)

codex mcp add stackbench --url https://mcp.computesage.com/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "stackbench": {
      "url": "https://mcp.computesage.com/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

search_evidence $0.00 free search of bounded public StackBench benchmark and failure evidence; use this for evidence-only requests.
check_deployment_fit $0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence.
predict_performance $0.05 USDC: predict configuration throughput, memory, and power from bounded StackBench evidence with confidence, missing metrics, and caveats.
recommend_deployment $0.25 USDC: recommend what to buy or run from bounded StackBench fit, performance, confidence, evidence, caveats, and economics only when supported.
generate_launch_config $0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/com.computesage/stackbench.svg)](https://lookupd.com/servers/com.computesage/stackbench)