{"data":{"node":{"slug":"lance-format-lance","name":"lance","tagline":"Open Lakehouse Format for Multimodal AI","github_url":"https://github.com/lance-format/lance","owner":"lance-format","repo":"lance","owner_avatar_url":"https://avatars.githubusercontent.com/u/243204601?v=4","primary_language":"Rust","stars":7120,"forks":867,"topics":["apache-arrow","computer-vision","data-analysis","data-analytics","data-centric","data-format","data-science","dataops","deep-learning","duckdb","embeddings","llms","machine-learning","mlops","python","rust"],"archived":false,"github_pushed_at":"2026-09-27T17:26:44+00:00","maintenance_label":"Very active","stars_delta_30d":220,"url":"https://www.graphcanon.com/tools/lance-format-lance","markdown_url":"https://www.graphcanon.com/tools/lance-format-lance.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lance-format-lance","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lance-format-lance"},"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"}],"tags":[{"slug":"apache-arrow","name":"apache-arrow"},{"slug":"computer-vision","name":"computer-vision"},{"slug":"data-analysis","name":"data-analysis"},{"slug":"data-analytics","name":"data-analytics"},{"slug":"data-centric","name":"data-centric"},{"slug":"data-format","name":"data-format"},{"slug":"data-science","name":"data-science"},{"slug":"dataops","name":"dataops"}],"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":["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":"lancedb-lancedb","name":"lancedb","tagline":"Developer-friendly OSS embedded retrieval library for multimodal AI","github_url":"https://github.com/lancedb/lancedb","owner":"lancedb","repo":"lancedb","owner_avatar_url":"https://avatars.githubusercontent.com/u/108903835?v=4","primary_language":"Rust","stars":11456,"forks":1057,"topics":["approximate-nearest-neighbor-search","image-search","nearest-neighbor-search","recommender-system","search-engine","semantic-search","similarity-search","vector-database"],"archived":false,"github_pushed_at":"2026-09-17T20:58:43+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/lancedb-lancedb","markdown_url":"https://www.graphcanon.com/tools/lancedb-lancedb.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lancedb-lancedb","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lancedb-lancedb","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":"activeloopai-deeplake","name":"deeplake","tagline":"AI Data Runtime for Agents","github_url":"https://github.com/activeloopai/deeplake","owner":"activeloopai","repo":"deeplake","owner_avatar_url":"https://avatars.githubusercontent.com/u/34816118?v=4","primary_language":"C++","stars":9239,"forks":722,"topics":["agent","agentic-rag","ai","clawbot","computer-vision","datalake","deep-learning","filesystem","large-language-models","llm","memory","mlops","multimodal","openclaw","postgres","pytorch","rag","skill","vector-database"],"archived":false,"github_pushed_at":"2026-05-21T15:28:00+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/activeloopai-deeplake","markdown_url":"https://www.graphcanon.com/tools/activeloopai-deeplake.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/activeloopai-deeplake","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=activeloopai-deeplake","shared_categories":["data-retrieval"]},{"slug":"delta-io-delta","name":"delta","tagline":"An open-source storage framework for building Lakehouse architecture with various compute engines and APIs","github_url":"https://github.com/delta-io/delta","owner":"delta-io","repo":"delta","owner_avatar_url":"https://avatars.githubusercontent.com/u/49767398?v=4","primary_language":"Scala","stars":9022,"forks":2185,"topics":["acid","analytics","big-data","delta-lake","spark"],"archived":false,"github_pushed_at":"2026-09-28T02:42:18+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/delta-io-delta","markdown_url":"https://www.graphcanon.com/tools/delta-io-delta.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/delta-io-delta","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=delta-io-delta","shared_categories":["data-retrieval"]},{"slug":"wangrongsheng-awesome-llm-resources","name":"awesome-LLM-resources","tagline":"Summary of the world's best LLM resources.","github_url":"https://github.com/WangRongsheng/awesome-LLM-resources","owner":"WangRongsheng","repo":"awesome-LLM-resources","owner_avatar_url":"https://avatars.githubusercontent.com/u/55651568?v=4","primary_language":null,"stars":8968,"forks":993,"topics":["awesome-list","book","course","large-language-models","llama","llm","mistral","openai","qwen","rag","retrieval-augmented-generation","webui"],"archived":false,"github_pushed_at":"2026-09-14T09:00:10+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/wangrongsheng-awesome-llm-resources","markdown_url":"https://www.graphcanon.com/tools/wangrongsheng-awesome-llm-resources.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/wangrongsheng-awesome-llm-resources","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=wangrongsheng-awesome-llm-resources","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":"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":["data-retrieval"]},{"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":["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"]}]}}