{"id":28619283,"url":"https://github.com/mlshukai/pamiq-core","last_synced_at":"2025-06-12T04:30:38.893Z","repository":{"id":267434906,"uuid":"901142155","full_name":"MLShukai/pamiq-core","owner":"MLShukai","description":"Framework for building AI agents with real-time adaptive learning capabilities.","archived":false,"fork":false,"pushed_at":"2025-06-10T07:53:36.000Z","size":2944,"stargazers_count":10,"open_issues_count":2,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-06-10T08:35:47.275Z","etag":null,"topics":["adaptive-learning","agent","ai","ami","autonomous-agents","autonomous-machine-intelligence","framework","machine","machine-learning","ml","python","real-time"],"latest_commit_sha":null,"homepage":"https://mlshukai.github.io/pamiq-core/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MLShukai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-12-10T05:45:44.000Z","updated_at":"2025-06-10T02:11:21.000Z","dependencies_parsed_at":"2024-12-10T10:36:06.390Z","dependency_job_id":"40e659a0-d40d-4839-aff2-4735f0c43e23","html_url":"https://github.com/MLShukai/pamiq-core","commit_stats":null,"previous_names":["mlshukai/pamiq-core"],"tags_count":10,"template":false,"template_full_name":null,"purl":"pkg:github/MLShukai/pamiq-core","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MLShukai%2Fpamiq-core","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MLShukai%2Fpamiq-core/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MLShukai%2Fpamiq-core/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MLShukai%2Fpamiq-core/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MLShukai","download_url":"https://codeload.github.com/MLShukai/pamiq-core/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MLShukai%2Fpamiq-core/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259397235,"owners_count":22851191,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["adaptive-learning","agent","ai","ami","autonomous-agents","autonomous-machine-intelligence","framework","machine","machine-learning","ml","python","real-time"],"created_at":"2025-06-12T04:30:36.181Z","updated_at":"2025-06-12T04:30:38.807Z","avatar_url":"https://github.com/MLShukai.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"![logo](./docs/images/logo.svg)\n\n# pamiq-core\n\n[![PyPI version](https://img.shields.io/pypi/v/pamiq-core.svg)](https://pypi.org/project/pamiq-core/)\n[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![Document Style](https://img.shields.io/badge/%20docstyle-google-3666d6.svg)](https://google.github.io/styleguide/pyguide.html#s3.8-comments-and-docstrings)\n[![Test](https://github.com/MLShukai/pamiq-core/actions/workflows/test.yml/badge.svg)](https://github.com/MLShukai/pamiq-core/actions/workflows/test.yml)\n[![Type Check](https://github.com/MLShukai/pamiq-core/actions/workflows/type-check.yml/badge.svg)](https://github.com/MLShukai/pamiq-core/actions/workflows/type-check.yml)\n[![Format \u0026 Lint (pre-commit)](https://github.com/MLShukai/pamiq-core/actions/workflows/pre-commit.yml/badge.svg)](https://github.com/MLShukai/pamiq-core/actions/workflows/pre-commit.yml)\n\n**pamiq-core** is a framework for building AI agents. Developed for P-AMI\\\u003cQ\u003e, it enables train and inference in parallel, allowing agents to adapt continuously during interaction with their environment.\n\n## ✨ Features\n\n- 🔄 **Parallel Architecture**: Simultaneous inference and training in separate threads\n- ⚡ **Real-time Adaptation**: Continuously update models during interaction\n- 🧵 **Thread-safe Design**: Robust synchronization mechanisms for parameter sharing and data transfers\n- 🔌 **Modular Components**: Easy-to-extend agent, environment, and model interfaces\n- 🛠️ **Comprehensive Tools**: Built-in state persistence, time control, and monitoring\n- 🌍 **Cross Platform**: Linux is the primary focus, but Windows and macOS are also supported. (However, some older macOS and Windows systems may have significantly less accurate time control.)\n\n## 📋 Requirements\n\n- Python 3.12+\n- PyTorch (optional, for torch integration)\n\n## 🚀 Quick Start\n\n### Installation\n\n```bash\n# Install with pip\npip install pamiq-core\n\n# Optional PyTorch integration\npip install pamiq-core[torch]\n```\n\n### Basic Example\n\n```python\nfrom pamiq_core import launch, Interaction, LaunchConfig\nfrom your_agent import YourAgent\nfrom your_environment import YourEnvironment\n\n# Create agent-environment interaction\ninteraction = Interaction(YourAgent(), YourEnvironment())\n\n# Launch the system\nlaunch(\n    interaction=interaction,\n    models=your_models,\n    data=your_data_buffers,\n    trainers=your_trainers,\n    config=LaunchConfig(\n        web_api_address=(\"localhost\", 8391),\n        max_uptime=300.0,  # 5 minutes\n    ),\n)\n```\n\nSee the [samples](samples/) directory for complete examples.\n\n### Remote CLI Control\n\nOnce the system is running, you can connect and control it remotely via the terminal using `pamiq-console`:\n\n```bash\n# Connect to local system\npamiq-console --host localhost --port 8391\n\n# Connect to remote system\npamiq-console --host 192.168.1.100 --port 8391\n```\n\n## 📚 Documentation\n\nFor comprehensive API documentation and detailed tutorials, please visit the [documentation website](https://mlshukai.github.io/pamiq-core/).\n\n## 🧩 Architecture\n\n![PAMIQ System Architecture](docs/images/system-architecture.svg)\n\npamiq-core implements a unique architecture that enables autonomous intelligence:\n\n1. **Concurrent Threads**: Separate threads for control, inference, and training\n2. **Parameter Sharing**: Thread-safe model parameter synchronization\n3. **Experience Collection**: Automatic buffering of data from environments, such as images and audio.\n4. **Continuous Learning**: Training models while simultaneously using them for decision making\n5. **State Persistence**: Saving and loading system state for resumable operation\n\n## 🤝 Contributing\n\nContributions are welcome! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on how to contribute to pamiq-core.\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 🔗 Related Projects\n\n- [pamiq-recorder](https://github.com/MLShukai/pamiq-recorder): Recording library for P-AMI\\\u003cQ\u003e\n- [pamiq-io](https://github.com/MLShukai/pamiq-io): I/O library for P-AMI\\\u003cQ\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlshukai%2Fpamiq-core","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmlshukai%2Fpamiq-core","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlshukai%2Fpamiq-core/lists"}