{"data":{"node":{"slug":"pachyderm-pachyderm","name":"pachyderm","tagline":"Data-Centric Pipelines and Data Versioning","github_url":"https://github.com/pachyderm/pachyderm","owner":"pachyderm","repo":"pachyderm","owner_avatar_url":"https://avatars.githubusercontent.com/u/10432478?v=4","primary_language":"Go","stars":6311,"forks":577,"topics":["analytics","big-data","containers","data-analysis","data-science","distributed-systems","docker","go","kubernetes","pachyderm"],"archived":false,"github_pushed_at":"2025-02-03T22:27:18+00:00","maintenance_label":"Dormant","stars_delta_30d":11,"url":"https://www.graphcanon.com/tools/pachyderm-pachyderm","markdown_url":"https://www.graphcanon.com/tools/pachyderm-pachyderm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pachyderm-pachyderm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pachyderm-pachyderm"},"categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"analytics","name":"analytics"},{"slug":"big-data","name":"big-data"},{"slug":"containers","name":"containers"},{"slug":"data-analysis","name":"data-analysis"},{"slug":"data-science","name":"data-science"},{"slug":"distributed-systems","name":"distributed-systems"},{"slug":"docker","name":"docker"},{"slug":"kubernetes","name":"kubernetes"}],"edges":[],"neighbours":[{"slug":"dagster-io-dagster","name":"dagster","tagline":"An orchestration platform for data assets","github_url":"https://github.com/dagster-io/dagster","owner":"dagster-io","repo":"dagster","owner_avatar_url":"https://avatars.githubusercontent.com/u/40032576?v=4","primary_language":"Python","stars":16144,"forks":2290,"topics":["analytics","dagster","data-engineering","data-integration","data-orchestrator","data-pipelines","data-science","etl","metadata","mlops","orchestration","python","scheduler","workflow","workflow-automation"],"archived":false,"github_pushed_at":"2026-09-11T19:05:31+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/dagster-io-dagster","markdown_url":"https://www.graphcanon.com/tools/dagster-io-dagster.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/dagster-io-dagster","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=dagster-io-dagster","shared_categories":[]},{"slug":"databendlabs-databend","name":"databend","tagline":"All-in-One Data Warehouse: Analytics, Search, AI, and Python Sandboxing Reimagined From Scratch.","github_url":"https://github.com/databendlabs/databend","owner":"databendlabs","repo":"databend","owner_avatar_url":"https://avatars.githubusercontent.com/u/80994548?v=4","primary_language":"Rust","stars":9444,"forks":897,"topics":["ai","bigdata","cloud-native","database","elasticsearch","geospatial","lakehouse","olap","rust","serverless","snowflake","sql","vector-database","vector-search"],"archived":false,"github_pushed_at":"2026-09-20T05:38:04+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/databendlabs-databend","markdown_url":"https://www.graphcanon.com/tools/databendlabs-databend.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/databendlabs-databend","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=databendlabs-databend","shared_categories":[]},{"slug":"mage-ai-mage-ai","name":"mage-ai","tagline":"Build, run and manage data pipelines for integrating and transforming data","github_url":"https://github.com/mage-ai/mage-ai","owner":"mage-ai","repo":"mage-ai","owner_avatar_url":"https://avatars.githubusercontent.com/u/69371472?v=4","primary_language":"Python","stars":8823,"forks":990,"topics":["artificial-intelligence","data","data-engineering","data-integration","data-pipelines","data-science","dbt","elt","etl","machine-learning","orchestration","pipeline","pipelines","python","reverse-etl","spark","sql","transformation"],"archived":false,"github_pushed_at":"2026-09-11T19:20:35+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/mage-ai-mage-ai","markdown_url":"https://www.graphcanon.com/tools/mage-ai-mage-ai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mage-ai-mage-ai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mage-ai-mage-ai","shared_categories":[]},{"slug":"ai-dynamo-dynamo","name":"dynamo","tagline":"A Datacenter Scale Distributed Inference Serving Framework","github_url":"https://github.com/ai-dynamo/dynamo","owner":"ai-dynamo","repo":"dynamo","owner_avatar_url":"https://avatars.githubusercontent.com/u/201626793?v=4","primary_language":"Rust","stars":8121,"forks":1601,"topics":["diffusion","disaggregated-serving","kubernetes","llm-inference","omni","routing-engine","rust","sglang","tensorrt-llm","vllm"],"archived":false,"github_pushed_at":"2026-09-19T17:01:54+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/ai-dynamo-dynamo","markdown_url":"https://www.graphcanon.com/tools/ai-dynamo-dynamo.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ai-dynamo-dynamo","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ai-dynamo-dynamo","shared_categories":[]},{"slug":"feast-dev-feast","name":"feast","tagline":"The Open Source Feature Store for AI/ML","github_url":"https://github.com/feast-dev/feast","owner":"feast-dev","repo":"feast","owner_avatar_url":"https://avatars.githubusercontent.com/u/57027613?v=4","primary_language":"Python","stars":7311,"forks":1451,"topics":["big-data","data-engineering","data-quality","data-science","feature-store","features","machine-learning","ml","mlops","python"],"archived":false,"github_pushed_at":"2026-09-26T16:51:49+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/feast-dev-feast","markdown_url":"https://www.graphcanon.com/tools/feast-dev-feast.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/feast-dev-feast","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=feast-dev-feast","shared_categories":[]},{"slug":"pditommaso-awesome-pipeline","name":"awesome-pipeline","tagline":"Curated list of pipeline toolkits","github_url":"https://github.com/pditommaso/awesome-pipeline","owner":"pditommaso","repo":"awesome-pipeline","owner_avatar_url":"https://avatars.githubusercontent.com/u/816968?v=4","primary_language":null,"stars":6624,"forks":650,"topics":["awesome-list","workflow"],"archived":false,"github_pushed_at":"2026-09-08T15:19:15+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/pditommaso-awesome-pipeline","markdown_url":"https://www.graphcanon.com/tools/pditommaso-awesome-pipeline.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pditommaso-awesome-pipeline","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pditommaso-awesome-pipeline","shared_categories":["developer-tools"]},{"slug":"treeverse-lakefs","name":"lakeFS","tagline":"Data version control for your data lake","github_url":"https://github.com/treeverse/lakeFS","owner":"treeverse","repo":"lakeFS","owner_avatar_url":"https://avatars.githubusercontent.com/u/58909255?v=4","primary_language":"Go","stars":5542,"forks":479,"topics":["apache-spark","apache-sparksql","aws-s3","azure-blob-storage","azure-storage","data-engineering","data-lake","data-quality","data-version-control","data-versioning","datalake","datalakes","git-for-data","go","golang","google-cloud-storage","hadoop-filesystem","lakefs","object-storage"],"archived":false,"github_pushed_at":"2026-09-25T16:49:12+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/treeverse-lakefs","markdown_url":"https://www.graphcanon.com/tools/treeverse-lakefs.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/treeverse-lakefs","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=treeverse-lakefs","shared_categories":[]},{"slug":"kubeflow-pipelines","name":"pipelines","tagline":"Machine Learning Pipelines for Kubeflow","github_url":"https://github.com/kubeflow/pipelines","owner":"kubeflow","repo":"pipelines","owner_avatar_url":"https://avatars.githubusercontent.com/u/33164907?v=4","primary_language":"Go","stars":4230,"forks":2136,"topics":["data-science","kubeflow","kubeflow-pipelines","kubernetes","machine-learning","mlops","pipeline"],"archived":false,"github_pushed_at":"2026-09-28T20:00:41+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/kubeflow-pipelines","markdown_url":"https://www.graphcanon.com/tools/kubeflow-pipelines.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/kubeflow-pipelines","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=kubeflow-pipelines","shared_categories":["model-training"]},{"slug":"ucbepic-docetl","name":"docetl","tagline":"A system for agentic LLM-powered data processing and ETL","github_url":"https://github.com/ucbepic/docetl","owner":"ucbepic","repo":"docetl","owner_avatar_url":"https://avatars.githubusercontent.com/u/88680502?v=4","primary_language":"Python","stars":4092,"forks":443,"topics":["agents","data","data-pipelines","document-analysis","document-processing","elt","etl","llm","python","semantic-data","unstructured-data","unstructured-data-analysis","workflow"],"archived":false,"github_pushed_at":"2026-09-05T16:55:18+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/ucbepic-docetl","markdown_url":"https://www.graphcanon.com/tools/ucbepic-docetl.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ucbepic-docetl","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ucbepic-docetl","shared_categories":[]},{"slug":"ploomber-ploomber","name":"ploomber","tagline":"The fastest way to build data pipelines. Develop iteratively, deploy anywhere.","github_url":"https://github.com/ploomber/ploomber","owner":"ploomber","repo":"ploomber","owner_avatar_url":"https://avatars.githubusercontent.com/u/60114551?v=4","primary_language":"Python","stars":3620,"forks":243,"topics":["data-engineering","data-science","jupyter","jupyter-notebooks","machine-learning","mlops","notebooks","papermill","pipelines","pycharm","vscode","workflow"],"archived":true,"github_pushed_at":"2025-05-29T22:02:03+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/ploomber-ploomber","markdown_url":"https://www.graphcanon.com/tools/ploomber-ploomber.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ploomber-ploomber","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ploomber-ploomber","shared_categories":["developer-tools"]},{"slug":"huggingface-datatrove","name":"datatrove","tagline":"Platform-agnostic customizable pipeline processing blocks for data processing and transformation.","github_url":"https://github.com/huggingface/datatrove","owner":"huggingface","repo":"datatrove","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":3379,"forks":312,"topics":[],"archived":false,"github_pushed_at":"2026-10-06T16:30:02+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/huggingface-datatrove","markdown_url":"https://www.graphcanon.com/tools/huggingface-datatrove.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-datatrove","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-datatrove","shared_categories":["model-training"]},{"slug":"microsoft-pai","name":"pai","tagline":"Resource scheduling and cluster management for AI","github_url":"https://github.com/microsoft/pai","owner":"microsoft","repo":"pai","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"JavaScript","stars":2694,"forks":554,"topics":["ai","artificial-intelligence","chainer","cloud","cluster-management","cluster-manager","gpu","gpu-cluster","gpu-computing","gpu-scheduler","jupyter","kubernetes","machine-learning","model-training","on-premise","pytorch","resource-management","scheduling","tensorflow"],"archived":false,"github_pushed_at":"2026-09-18T03:17:30+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/microsoft-pai","markdown_url":"https://www.graphcanon.com/tools/microsoft-pai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-pai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-pai","shared_categories":["model-training"]}]}}