GraphCanon
Home/AI Agents/myclaw-bench
myclaw-bench logo

myclaw-bench

LeoYeAI/myclaw-bench

Benchmark for AI agents on OpenClaw

GitHub Website

GraphCanon updated 3w · GitHub synced 3w · 28 views this month

227 stars38 forksLast push 1mo Python MIT

Decision brief

myclaw-bench is a benchmark suite comprising 45 tasks across four tiers designed for evaluating AI agents within the OpenClaw platform.

Good fit when

  • Use myclaw-bench if you are developing AI agents specifically for deployment on the OpenClaw platform, as it offers a precise evaluation tailored to this ecosystem.
  • Select this benchmark suite when your AI agent development involves real-world testing scenarios, given that tasks are derived from over 10,000 real agent sessions.

Avoid when

  • Avoid using myclaw-bench if your AI agents will not be deployed on the OpenClaw platform, as its benchmarks are specifically designed to test within this framework.
  • Do not use if you require synthetic tests for controlling variables in a highly abstracted scenario, since myclaw-bench exclusively leverages real agent session data.
Requirements:
Requires Python version 3.10 or higher to execute the benchmark tasks.; Necessitates installation of the 'uv' package manager from Astral for dependencies management.

Observed Jul 17, 2026 · Source: enrich:decision_facts

myclaw-bench alternativesTrust report

Verify the decision

Maintenance and security

Full trust report
Maintenance
Active (8d since push)
As of 3w
Provenance
Not a fork · Personal account
As of 3w
Security (OSV)
No lockfile
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install myclaw-bench
PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

A suite of 45 benchmark tasks across four tiers designed to test the performance of AI agents within the OpenClaw platform.

Capability facts

Languages
python

Source: github.language · Jul 29, 2026

Categories

AI AgentsEvaluation & Observability

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 29, 2026)

- Python 3.10+
Source link

Tags

ai-agent-evaluationbenchmarking-toolsopenclaw

README

Requirements

  • Python 3.10+
  • uv package manager
  • A running OpenClaw instance
  • API key for the model being tested

License

MIT — see LICENSE for details.

Built by MyClaw.ai — from 10,000+ real agent sessions, not synthetic tests.

For agents

This page has a .md twin and JSON over the API.

/tools/leoyeai-myclaw-bench.mdGET /api/graphcanon/tools/leoyeai-myclaw-benchGET /api/graphcanon/graph?tool=leoyeai-myclaw-bench

Was this helpful?

Anonymous feedback helps us improve pages and translations.