{"data":{"slug":"leoyeai-myclaw-bench","name":"myclaw-bench","tagline":"Benchmark for AI agents on OpenClaw","github_url":"https://github.com/LeoYeAI/myclaw-bench","owner":"LeoYeAI","repo":"myclaw-bench","owner_avatar_url":"https://avatars.githubusercontent.com/u/121472001?v=4","primary_language":"Python","stars":223,"forks":36,"topics":["agent-testing","ai-agent","ai-benchmark","benchmark","llm-evaluation","myclaw","openclaw"],"archived":false,"github_pushed_at":"2026-07-20T08:48:41+00:00","maintenance_label":"Steady","stars_delta_30d":-4,"url":"https://www.graphcanon.com/tools/leoyeai-myclaw-bench","markdown_url":"https://www.graphcanon.com/tools/leoyeai-myclaw-bench.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/leoyeai-myclaw-bench","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=leoyeai-myclaw-bench","description":"The definitive benchmark for AI agents on OpenClaw. 45 tasks across 4 tiers. Powered by MyClaw.ai","homepage_url":"https://myclaw.ai","license":"MIT","open_issues":2,"watchers":3,"ai_summary":"A suite of 45 benchmark tasks across four tiers designed to test the performance of AI agents within the OpenClaw platform.","readme_excerpt":"## Requirements\n\n- Python 3.10+\n- [uv](https://docs.astral.sh/uv/) package manager\n- A running OpenClaw instance\n- API key for the model being tested\n\n---\n\n## License\n\nMIT — see [LICENSE](LICENSE) for details.\n\n---\n\n*Built by [MyClaw.ai](https://myclaw.ai) — from 10,000+ real agent sessions, not synthetic tests.*","github_created_at":"2026-03-09T03:44:43+00:00","created_at":"2026-07-11T12:01:18.246545+00:00","updated_at":"2026-09-20T06:59:49.291997+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"ai-agent-evaluation","name":"ai-agent-evaluation"},{"slug":"benchmarking-tools","name":"benchmarking-tools"},{"slug":"openclaw","name":"openclaw"}],"trust":{"provenance":{"is_fork":false,"github_id":1176468769,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:59:46.795Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":61,"last_release_at":"2026-03-09T03:46:20Z","stars_delta_30d":-4,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:01:27.885Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:59:47.801Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-20T06:59:47.801Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T06:59:47.801Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires Python version 3.10 or higher to execute the benchmark tasks.","Necessitates installation of the 'uv' package manager from Astral for dependencies management."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["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.","Choose myclaw-bench if you need detailed performance insights across four tiers of difficulty for comprehensive and granular testing."],"when_not_to_use":["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."],"source":"enrich:decision_facts","observed_at":"2026-07-17T01:14:23.375Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Requires Python version 3.10 or higher to execute the benchmark tasks.; Necessitates installation of the 'uv' package manager from Astral for dependencies management."},{"label":"Adopt for","value":"myclaw-bench is a benchmark suite comprising 45 tasks across four tiers designed for evaluating AI agents within the OpenClaw platform."}]}}