{"id":26506867,"url":"https://github.com/msoedov/meta_loop","last_synced_at":"2025-03-20T22:57:18.155Z","repository":{"id":279363282,"uuid":"937785441","full_name":"msoedov/meta_loop","owner":"msoedov","description":"An agent-optimization framework ✨","archived":false,"fork":false,"pushed_at":"2025-03-13T11:42:15.000Z","size":1844,"stargazers_count":1,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-13T12:23:13.139Z","etag":null,"topics":["agent-framework","agent-frameworks","agentic-workflow","crewai","pydantic-ai"],"latest_commit_sha":null,"homepage":"","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/msoedov.png","metadata":{"files":{"readme":"Readme.md","changelog":null,"contributing":null,"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}},"created_at":"2025-02-23T22:03:33.000Z","updated_at":"2025-03-13T11:42:08.000Z","dependencies_parsed_at":"2025-03-13T12:21:22.230Z","dependency_job_id":"97076389-a787-4ba9-b69b-8db60c30e0e9","html_url":"https://github.com/msoedov/meta_loop","commit_stats":null,"previous_names":["msoedov/meta_agent"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/msoedov%2Fmeta_loop","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/msoedov%2Fmeta_loop/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/msoedov%2Fmeta_loop/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/msoedov%2Fmeta_loop/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/msoedov","download_url":"https://codeload.github.com/msoedov/meta_loop/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244706519,"owners_count":20496571,"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":["agent-framework","agent-frameworks","agentic-workflow","crewai","pydantic-ai"],"created_at":"2025-03-20T22:57:17.754Z","updated_at":"2025-03-20T22:57:18.136Z","avatar_url":"https://github.com/msoedov.png","language":"Python","readme":"\n\u003cp align=\"center\"\u003e \u003ch1 align=\"center\"\u003eMeta Loop\u003c/h1\u003e \u003cp align=\"center\"\u003e An automatic agent optimization framework for generating, evaluating, and selecting top-performing agents.\u003cbr /\u003e Define your task, and let Meta Loop discover the perfect solution.\u003cbr /\u003e \u003ca href=\"#\"\u003eExplore the Docs »\u003c/a\u003e · \u003ca href=\"#\"\u003eReport a Bug »\u003c/a\u003e \u003c/p\u003e \u003c/p\u003e \u003cp align=\"center\"\u003e \u003ca href=\"#\"\u003e \u003cimg alt=\"GitHub Last Commit\" src=\"https://img.shields.io/github/last-commit/msoedov/meta_loop?style=for-the-badge\u0026logo=git\u0026labelColor=000000\u0026color=6A35FF\" /\u003e \u003c/a\u003e \u003ca href=\"#\"\u003e \u003cimg alt=\"GitHub Repo Size\" src=\"https://img.shields.io/github/repo-size/msoedov/meta_loop?style=for-the-badge\u0026logo=database\u0026labelColor=000000\u0026color=yellow\" /\u003e \u003c/a\u003e \u003ca href=\"#\"\u003e \u003cimg alt=\"GitHub License\" src=\"https://img.shields.io/github/license/msoedov/meta_loop?style=for-the-badge\u0026logo=codeigniter\u0026labelColor=000000\u0026color=FFCC19\" /\u003e \u003c/a\u003e \u003ca href=\"https://pypi.org/project/meta_loop/\"\u003e \u003cimg alt=\"PyPI Version\" src=\"https://img.shields.io/pypi/v/meta_loop?style=for-the-badge\u0026logo=pypi\u0026labelColor=000000\u0026color=00CCFF\" /\u003e \u003c/a\u003e \u003c/p\u003e\n\nMeta Agent is a powerful, imperative, define-by-run framework designed to simplify agent development. It generates 16 candidate \"probes\" with varied configurations, evaluates them against customizable metrics, and selects the best-performing agent for your task. Whether you're analyzing data, predicting outcomes, or automating workflows, Meta Loop optimizes the process for you.\n## ✨ Features\n\n- Automated Agent Generation\n- Creates 16 unique agent \"probes\" with diverse configurations tailored to your task.\n- Customizable Evaluation\n- Scores probes using built-in metrics (e.g., accuracy, speed) or your own custom evaluation function.\n- Framework Flexibility\n- Built with Pydantic-AI by default, with seamless support for frameworks like AutoGen or CrewAI.\n- Extensible Design\n- Easily adapt agent roles, tools, and evaluation criteria to suit your specific needs.\n\n\n## 📦 Installation\n\nInstall Meta Agent with a single command:\n```shell\npip install meta_loop\n\n```\n## 🚀 Quick Start\n\nGet started in just a few lines of code. Below are examples to showcase Meta Agent’s capabilities.\nBasic Usage\n\nGenerate an agent to analyze customer reviews and predict sentiment:\n```python\nimport meta_loop\n\n# Build and optimize an agent\nbest_agent = meta_loop.build_agent(\n    instruction=\"Create an agent to analyze customer reviews and predict sentiment.\",\n    probe_count=16,\n    framework=\"crewai\"\n)\n\n# View the selected agent's details\nprint(best_agent.details)\n```\n### Custom Evaluation Function\n\nDefine your own scoring logic to evaluate probes:\n```python\nimport meta_loop\nimport random\n\n# Custom evaluation function\ndef custom_eval(trial: meta_loop.Trial) -\u003e float:\n    return random.random()  # Replace with your own metric\n\n# Build an agent with custom evaluation\nbest_agent = meta_loop.build_agent(\n    instruction=\"Create an agent to analyze customer reviews and predict sentiment.\",\n    probe_count=16,\n    framework=\"crewai\",\n    eval_fn=custom_eval\n)\n\nprint(best_agent.details)\n```\n### Using a Test Dataset\n\nProvide a dataset to evaluate agents against specific inputs and expected outputs:\n```python\nimport meta_loop\n\n# Build an agent with a test dataset\nbest_agent = meta_loop.build_agent(\n    instruction=\"Create an agent to analyze customer reviews and predict sentiment.\",\n    probe_count=16,\n    framework=\"crewai\",\n    test_dataset=meta_loop.dataset(\n        (\"Great product, love it!\", 0.9),  # (input, expected_score)\n        (\"Terrible service, very disappointed.\", 0.2),\n        (\"It's okay, nothing special.\", 0.5)\n    )\n)\n\nprint(best_agent.details)\n```\n\n## 🛠️ How It Works\n\n- Define Your Task: Provide a task description (e.g., \"analyze customer reviews\").\n- Generate Probes: Meta Agent creates 16 agent configurations with varying parameters.\n- Evaluate Performance: Each probe is scored based on your chosen metrics or dataset.\n- Select the Best: The top-performing agent is returned, ready for use.\n\n## 📚 Documentation\n\nFor more details, check out the official documentation (coming soon!).\n## 🤝 Contributing\n\nWe welcome contributions! Please see our contribution guidelines and feel free to submit issues or pull requests.\n\n## 📬 Get in Touch\n\nHave questions? Join our community or reach out:\n\n- Discord (coming soon!)\n- GitHub Issues\n","funding_links":[],"categories":["Python"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmsoedov%2Fmeta_loop","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmsoedov%2Fmeta_loop","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmsoedov%2Fmeta_loop/lists"}