├── .github ├── FUNDING.yml └── workflows │ └── ci.yml ├── .gitignore ├── CHANGELOG.md ├── CONTRIBUTING.md ├── LICENSE ├── Makefile ├── README.md ├── ai_agents_reality_check ├── __init__.py ├── agent_benchmark.py ├── agents │ ├── __init__.py │ ├── enhanced_executor.py │ ├── marketing │ │ ├── __init__.py │ │ ├── marketing_agent.py │ │ ├── marketing_executor.py │ │ ├── marketing_memory.py │ │ └── marketing_planner.py │ ├── real │ │ ├── __init__.py │ │ ├── real_agent.py │ │ ├── real_executor.py │ │ ├── real_memory.py │ │ ├── real_planner.py │ │ ├── real_recovery.py │ │ └── real_tracer.py │ ├── recovery.py │ ├── tracer.py │ └── wrapper │ │ ├── __init__.py │ │ ├── wrapper_agent.py │ │ ├── wrapper_executor.py │ │ ├── wrapper_memory.py │ │ └── wrapper_utils.py ├── cli.py ├── ensemble │ ├── __init__.py │ └── ensemble_benchmark.py ├── logging_config.py ├── types.py └── utils │ ├── __init__.py │ ├── enhanced_statistics.py │ └── helpers.py ├── docs ├── EVALUATION.md ├── USAGE.md └── assets │ ├── ai_agents_reality_check_v0.1.0.jpeg │ └── screenshots │ ├── core_benchmark_results.png │ ├── enhanced_benchmark_results.png │ ├── make_run_ensemble_output.png │ └── network_resilience_results.png ├── pyproject.toml ├── schemas └── trace │ └── agent_subgoal_trace.schema.json ├── tests ├── __init__.py └── unit │ ├── __init__.py │ ├── test_marketing_agent.py │ ├── test_real_agent.py │ ├── test_types.py │ ├── test_utils.py │ └── test_wrapper_agent.py └── uv.lock /.github/FUNDING.yml: -------------------------------------------------------------------------------- 1 | github: ["Cre4T3Tiv3"] -------------------------------------------------------------------------------- /.github/workflows/ci.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/.github/workflows/ci.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/.gitignore -------------------------------------------------------------------------------- /CHANGELOG.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/CHANGELOG.md -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/LICENSE -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/README.md -------------------------------------------------------------------------------- /ai_agents_reality_check/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/__init__.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agent_benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agent_benchmark.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/__init__.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/enhanced_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/enhanced_executor.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/marketing/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/marketing/__init__.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/marketing/marketing_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/marketing/marketing_agent.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/marketing/marketing_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/marketing/marketing_executor.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/marketing/marketing_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/marketing/marketing_memory.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/marketing/marketing_planner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/marketing/marketing_planner.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/real/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/real/__init__.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/real/real_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/real/real_agent.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/real/real_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/real/real_executor.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/real/real_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/real/real_memory.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/real/real_planner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/real/real_planner.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/real/real_recovery.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/real/real_recovery.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/real/real_tracer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/real/real_tracer.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/recovery.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/recovery.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/tracer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/tracer.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/wrapper/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/wrapper/__init__.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/wrapper/wrapper_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/wrapper/wrapper_agent.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/wrapper/wrapper_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/wrapper/wrapper_executor.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/wrapper/wrapper_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/wrapper/wrapper_memory.py -------------------------------------------------------------------------------- /ai_agents_reality_check/agents/wrapper/wrapper_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/agents/wrapper/wrapper_utils.py -------------------------------------------------------------------------------- /ai_agents_reality_check/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/cli.py -------------------------------------------------------------------------------- /ai_agents_reality_check/ensemble/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/ensemble/__init__.py -------------------------------------------------------------------------------- /ai_agents_reality_check/ensemble/ensemble_benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/ensemble/ensemble_benchmark.py -------------------------------------------------------------------------------- /ai_agents_reality_check/logging_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/logging_config.py -------------------------------------------------------------------------------- /ai_agents_reality_check/types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/types.py -------------------------------------------------------------------------------- /ai_agents_reality_check/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/utils/__init__.py -------------------------------------------------------------------------------- /ai_agents_reality_check/utils/enhanced_statistics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/utils/enhanced_statistics.py -------------------------------------------------------------------------------- /ai_agents_reality_check/utils/helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/ai_agents_reality_check/utils/helpers.py -------------------------------------------------------------------------------- /docs/EVALUATION.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/docs/EVALUATION.md -------------------------------------------------------------------------------- /docs/USAGE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/docs/USAGE.md -------------------------------------------------------------------------------- /docs/assets/ai_agents_reality_check_v0.1.0.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/docs/assets/ai_agents_reality_check_v0.1.0.jpeg -------------------------------------------------------------------------------- /docs/assets/screenshots/core_benchmark_results.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/docs/assets/screenshots/core_benchmark_results.png -------------------------------------------------------------------------------- /docs/assets/screenshots/enhanced_benchmark_results.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/docs/assets/screenshots/enhanced_benchmark_results.png -------------------------------------------------------------------------------- /docs/assets/screenshots/make_run_ensemble_output.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/docs/assets/screenshots/make_run_ensemble_output.png -------------------------------------------------------------------------------- /docs/assets/screenshots/network_resilience_results.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/docs/assets/screenshots/network_resilience_results.png -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/pyproject.toml -------------------------------------------------------------------------------- /schemas/trace/agent_subgoal_trace.schema.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/schemas/trace/agent_subgoal_trace.schema.json -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/tests/__init__.py -------------------------------------------------------------------------------- /tests/unit/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/tests/unit/__init__.py -------------------------------------------------------------------------------- /tests/unit/test_marketing_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/tests/unit/test_marketing_agent.py -------------------------------------------------------------------------------- /tests/unit/test_real_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/tests/unit/test_real_agent.py -------------------------------------------------------------------------------- /tests/unit/test_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/tests/unit/test_types.py -------------------------------------------------------------------------------- /tests/unit/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/tests/unit/test_utils.py -------------------------------------------------------------------------------- /tests/unit/test_wrapper_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/tests/unit/test_wrapper_agent.py -------------------------------------------------------------------------------- /uv.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Cre4T3Tiv3/ai-agents-reality-check/HEAD/uv.lock --------------------------------------------------------------------------------