{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "artificialanalysis-aa-agentperf-local--live-tool-calling-benchmark",
 "repo": "ArtificialAnalysis/aa-agentperf-local",
 "repo_url": "https://github.com/ArtificialAnalysis/aa-agentperf-local",
 "repo_slug": "artificialanalysis-aa-agentperf-local",
 "title": "Measure real tool time with live Docker tool calls",
 "page_title": "How to measure real tool time with live Docker tool calls with Aa Agentperf Local",
 "summary": "Run the recorded shell commands in Docker containers so tool time is measured, not skipped.",
 "who": "A researcher or infrastructure engineer who needs agent timings that include real tool execution, not sleep estimates.",
 "problem": "By default the replay skips tool time between turns, so end-to-end agent timing can be understated.",
 "outcome": "A run with live tool timing and a results directory that includes tools.json.",
 "steps": [
  "Run `scripts/install-swebench-validation.sh` on arm64 hosts only, once",
  "Run `scripts/build-default-containers.sh`",
  "Run `uv run agentperf-local run --base-url http://127.0.0.1:8080/v1 --model served-model --output-dir results/live-tools --tool-mode live` (inferred, check the README)",
  "Read tools.json and summary.json in results/live-tools"
 ],
 "agent_prompt": "Using the agentperf-local repo from ArtificialAnalysis, build the default containers, then run `agentperf-local run` with --tool-mode live against <base-url> with model <model-name>, writing to results/<name>. Expect tools.json and summary.json in that directory. Verify that --live-network none was passed unless network access was explicitly needed.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "2 hours",
 "basis": "readme",
 "caveat": "Docker is not a security boundary and access to the Docker daemon is equivalent to root on most hosts, so review the security caveats before running.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "uv installed (it fetches Python 3.12 if needed)",
  "A model server you already run with an OpenAI-compatible API, or a framework the tool can start (llama.cpp, vLLM, SGLang, or Splash on Apple Silicon)",
  "For full results, a server or device that can run a 65,536-token context at batch size 1",
  "Docker only if you want live tool calling"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "remote-script",
   "notice": "The build scripts pull or build third-party images and clone the SWE-bench harness from GitHub, and the recorded shell commands are untrusted input."
  }
 ],
 "best": false,
 "score": 0.6,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/artificialanalysis-aa-agentperf-local/live-tool-calling-benchmark/",
 "md": "https://dedupedai.com/use-cases/artificialanalysis-aa-agentperf-local/live-tool-calling-benchmark/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/artificialanalysis-aa-agentperf-local--live-tool-calling-benchmark.json",
 "api_version": "v1"
}