{"id":31328117,"url":"https://github.com/overeasy-sh/overeasy","last_synced_at":"2025-09-25T23:57:25.898Z","repository":{"id":234995350,"uuid":"789873310","full_name":"overeasy-sh/overeasy","owner":"overeasy-sh","description":"Orchestrate zero-shot computer vision models","archived":false,"fork":false,"pushed_at":"2024-08-20T12:30:36.000Z","size":48774,"stargazers_count":396,"open_issues_count":2,"forks_count":14,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-09-02T14:19:20.818Z","etag":null,"topics":["agent","agents","artificial-intelligence","computer-vision","llms","open-source","vision-framework"],"latest_commit_sha":null,"homepage":"https://docs.overeasy.sh/","language":"HTML","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/overeasy-sh.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":"2024-04-21T19:29:37.000Z","updated_at":"2025-08-21T07:48:33.000Z","dependencies_parsed_at":"2024-04-23T06:39:26.026Z","dependency_job_id":"783b954a-0798-4315-9327-929d29e5c03a","html_url":"https://github.com/overeasy-sh/overeasy","commit_stats":null,"previous_names":["overeasy-sh/overeasy"],"tags_count":30,"template":false,"template_full_name":null,"purl":"pkg:github/overeasy-sh/overeasy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/overeasy-sh%2Fovereasy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/overeasy-sh%2Fovereasy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/overeasy-sh%2Fovereasy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/overeasy-sh%2Fovereasy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/overeasy-sh","download_url":"https://codeload.github.com/overeasy-sh/overeasy/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/overeasy-sh%2Fovereasy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":276999964,"owners_count":25742818,"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","status":"online","status_checked_at":"2025-09-25T02:00:09.612Z","response_time":80,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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","agents","artificial-intelligence","computer-vision","llms","open-source","vision-framework"],"created_at":"2025-09-25T23:57:24.839Z","updated_at":"2025-09-25T23:57:25.886Z","avatar_url":"https://github.com/overeasy-sh.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ch1 align=\"center\"\u003e 🥚 Overeasy\n\u003cbr/\u003e\n\u003cspan align=\"center\"\u003e\n   \u003ca href=\"https://pypi.org/project/overeasy/\" target=\"_blank\"\u003e\u003cimg src=\"https://img.shields.io/pypi/v/overeasy.svg?style=flat-square\u0026label=PyPI+Overeasy\" alt=\"Issues\"\u003e\u003c/a\u003e\n   \u003ca href=\"https://github.com/overeasy-sh/overeasy/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/license-MIT-blue\" alt=\"License\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://docs.overeasy.sh\"\u003e\u003cimg src=\"https://img.shields.io/badge/Docs-informational\" alt=\"Docs\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://colab.research.google.com/drive/1Mkx9S6IG5130wiP9WmwgINiyw0hPsh3c?usp=sharing#scrollTo=L0_U27WJaTNO\"\"\u003e\u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Colab Demo\"\u003e\u003c/a\u003e\n\u003c/span\u003e\n \u003c/h1\u003e\n\n\n\n\n\u003cp \u003e \u003ch3 align=\"center\"\u003eCreate powerful zero-shot vision models! \u003c/h3\u003e \u003c/p\u003e\n\n\nOvereasy allows you to chain zero-shot vision models to create custom end-to-end pipelines for tasks like:\n\n- 📦 Bounding Box Detection\n- 🏷️ Classification\n- 🖌️ Segmentation (Coming Soon!)\n\nAll of this can be achieved without needing to collect and annotate large training datasets. \n\nOvereasy makes it simple to combine pre-trained zero-shot models to build powerful custom computer vision solutions.\n\n\n## Installation\nIt's as easy as\n```bash\npip install overeasy\n```\n\nFor installing extras refer to our [Docs](https://docs.overeasy.sh/installation/installing-extras).\n\n## Key Features\n- `🤖 Agents`: Specialized tools that perform specific image processing tasks.\n- `🧩 Workflows`: Define a sequence of Agents to process images in a structured manner.\n- `🔗 Execution Graphs`: Manage and visualize the image processing pipeline.\n- `🔎 Detections`: Represent bounding boxes, segmentation, and classifications.\n\n\n## Documentation \nFor more details on types, library structure, and available models please refer to our [Docs](https://docs.overeasy.sh).\n\n## Example Usage \n\n\u003e Note: If you don't have a local GPU, you can run our examples by making a copy of this [Colab notebook](https://colab.research.google.com/drive/1Mkx9S6IG5130wiP9WmwgINiyw0hPsh3c?usp=sharing#scrollTo=L0_U27WJaTNO).\n\n\nDownload example image\n```bash\n!wget https://github.com/overeasy-sh/overeasy/blob/73adbaeba51f532a7023243266da826ed1ced6ec/examples/construction.jpg?raw=true -O construction.jpg\n```\n\nExample workflow to identify if a person is wearing a PPE on a work site:\n```python\nfrom overeasy import *\nfrom overeasy.models import OwlV2\nfrom PIL import Image\n\nworkflow = Workflow([\n    # Detect each head in the input image\n    BoundingBoxSelectAgent(classes=[\"person's head\"], model=OwlV2()),\n    # Applies Non-Maximum Suppression to remove overlapping bounding boxes\n    NMSAgent(iou_threshold=0.5, score_threshold=0),\n    # Splits the input image into images of each detected head\n    SplitAgent(),\n    # Classifies the split images using CLIP\n    ClassificationAgent(classes=[\"hard hat\", \"no hard hat\"]),\n    # Maps the returned class names\n    ClassMapAgent({\"hard hat\": \"has ppe\", \"no hard hat\": \"no ppe\"}),\n    # Combines results back into a BoundingBox Detection\n    JoinAgent()\n])\n\nimage = Image.open(\"./construction.jpg\")\nresult, graph = workflow.execute(image)\nworkflow.visualize(graph)\n```\n\n### Diagram\n\nHere's a diagram of this workflow. Each layer in the graph represents a step in the workflow:\n\u003c!-- \n\u003cimg src=\"./assets/graph-diagram.png\" alt=\"ExecutionGraph\"/\u003e --\u003e\n\n\u003cpicture\u003e\n  \u003csource media=\"(prefers-color-scheme: dark)\" srcset=\"https://raw.githubusercontent.com/overeasy-sh/overeasy/main/assets/graph-diagram-dark.png\"\u003e\n  \u003csource media=\"(prefers-color-scheme: light)\" srcset=\"https://raw.githubusercontent.com/overeasy-sh/overeasy/main/assets/graph-diagram.png\"\u003e\n  \u003cimg alt=\"Diagram\" src=\"./assets/graph-diagram.png\"\u003e\n\u003c/picture\u003e\n\nThe image and data attributes in each node are used together to visualize the current state of the workflow. Calling the  `visualize` function on the workflow will spawn a Gradio instance that looks like [this](https://overeasy-sh.github.io/gradio-example/Gradio.html). \n\n## Support\nIf you have any questions or need assistance, please open an issue or reach out to us at help@overeasy.sh.\n\n\nLet's build amazing vision models together 🍳!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fovereasy-sh%2Fovereasy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fovereasy-sh%2Fovereasy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fovereasy-sh%2Fovereasy/lists"}