GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026
52views this month
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
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (61d since push)
- As of Sep 20, 2026
- Provenance
- Not a fork · Personal account
- As of Sep 20, 2026
- Security (OSV)
- No lockfile
- As of Jul 11, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install myclaw-benchSimilar 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 · Sep 20, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
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.