{"data":{"node":{"slug":"ml6team-fondant","name":"fondant","tagline":"Production-ready data processing made easy and shareable","github_url":"https://github.com/ml6team/fondant","owner":"ml6team","repo":"fondant","owner_avatar_url":"https://avatars.githubusercontent.com/u/36703417?v=4","primary_language":"Python","stars":359,"forks":28,"topics":["data-processing","fine-tuning","foundation-models","machine-learning","pipeline","python"],"archived":false,"github_pushed_at":"2026-02-20T07:28:05+00:00","maintenance_label":"Slowing","stars_delta_30d":1,"url":"https://www.graphcanon.com/tools/ml6team-fondant","markdown_url":"https://www.graphcanon.com/tools/ml6team-fondant.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ml6team-fondant","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ml6team-fondant"},"categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"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":"data-processing","name":"data-processing"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"foundation-models","name":"foundation models"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"pipeline","name":"pipeline"},{"slug":"python","name":"python"}],"edges":[],"neighbours":[{"slug":"pathwaycom-llm-app","name":"llm-app","tagline":"Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data","github_url":"https://github.com/pathwaycom/llm-app","owner":"pathwaycom","repo":"llm-app","owner_avatar_url":"https://avatars.githubusercontent.com/u/25750857?v=4","primary_language":"Jupyter Notebook","stars":58920,"forks":1498,"topics":["chatbot","hugging-face","llm","llm-local","llm-prompting","llm-security","llmops","machine-learning","open-ai","pathway","rag","real-time","retrieval-augmented-generation","vector-database","vector-index"],"archived":false,"github_pushed_at":"2026-07-05T17:59:07+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/pathwaycom-llm-app","markdown_url":"https://www.graphcanon.com/tools/pathwaycom-llm-app.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pathwaycom-llm-app","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pathwaycom-llm-app","shared_categories":["model-training","data-retrieval"]},{"slug":"sinaptik-ai-pandas-ai","name":"pandas-ai","tagline":"Chat with your database or your datalake using LLMs and RAG.","github_url":"https://github.com/sinaptik-ai/pandas-ai","owner":"sinaptik-ai","repo":"pandas-ai","owner_avatar_url":"https://avatars.githubusercontent.com/u/154438448?v=4","primary_language":"Python","stars":23746,"forks":2342,"topics":["ai","csv","data","data-analysis","data-science","data-visualization","database","datalake","gpt-4","llm","pandas","sql","text-to-sql"],"archived":false,"github_pushed_at":"2025-10-28T10:02:13+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/sinaptik-ai-pandas-ai","markdown_url":"https://www.graphcanon.com/tools/sinaptik-ai-pandas-ai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sinaptik-ai-pandas-ai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sinaptik-ai-pandas-ai","shared_categories":["data-retrieval"]},{"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":["data-retrieval"]},{"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":["data-retrieval"]},{"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":["data-retrieval"]},{"slug":"alteryx-featuretools","name":"featuretools","tagline":"An open source python library for automated feature engineering","github_url":"https://github.com/alteryx/featuretools","owner":"alteryx","repo":"featuretools","owner_avatar_url":"https://avatars.githubusercontent.com/u/12972388?v=4","primary_language":"Python","stars":7683,"forks":915,"topics":["automated-feature-engineering","automated-machine-learning","automl","data-science","feature-engineering","machine-learning","python","scikit-learn"],"archived":false,"github_pushed_at":"2026-09-11T08:13:00+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/alteryx-featuretools","markdown_url":"https://www.graphcanon.com/tools/alteryx-featuretools.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alteryx-featuretools","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alteryx-featuretools","shared_categories":["model-training"]},{"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":["data-retrieval"]},{"slug":"datajuicer-data-juicer","name":"data-juicer","tagline":"Data processing for and with foundation models","github_url":"https://github.com/datajuicer/data-juicer","owner":"datajuicer","repo":"data-juicer","owner_avatar_url":"https://avatars.githubusercontent.com/u/223222708?v=4","primary_language":"Python","stars":6897,"forks":404,"topics":["data","data-analysis","data-pipeline","data-processing","data-science","data-visualization","foundation-models","instruction-tuning","large-language-models","llm","llms","multi-modal","pre-training","synthetic-data"],"archived":false,"github_pushed_at":"2026-08-13T09:19:31+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/datajuicer-data-juicer","markdown_url":"https://www.graphcanon.com/tools/datajuicer-data-juicer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/datajuicer-data-juicer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=datajuicer-data-juicer","shared_categories":["model-training","data-retrieval"]},{"slug":"tensorchord-awesome-llmops","name":"Awesome-LLMOps","tagline":"An awesome & curated list of best LLMOps tools for developers","github_url":"https://github.com/tensorchord/Awesome-LLMOps","owner":"tensorchord","repo":"Awesome-LLMOps","owner_avatar_url":"https://avatars.githubusercontent.com/u/100543303?v=4","primary_language":"Shell","stars":5941,"forks":1058,"topics":["ai-development-tools","awesome-list","llmops","mlops"],"archived":false,"github_pushed_at":"2026-05-21T09:12:50+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/tensorchord-awesome-llmops","markdown_url":"https://www.graphcanon.com/tools/tensorchord-awesome-llmops.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tensorchord-awesome-llmops","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tensorchord-awesome-llmops","shared_categories":["model-training","data-retrieval"]},{"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":["data-retrieval"]},{"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":[]},{"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","data-retrieval"]}]}}