{"data":{"node":{"slug":"eventual-inc-daft","name":"Daft","tagline":"High-performance data engine for AI and multimodal workloads in Rust.","github_url":"https://github.com/Eventual-Inc/Daft","owner":"Eventual-Inc","repo":"Daft","owner_avatar_url":"https://avatars.githubusercontent.com/u/98941975?v=4","primary_language":"Rust","stars":5779,"forks":561,"topics":["ai-engineering","ai-pipeline","arrow","artificial-intelligence","big-data","data-engineering","distributed","distributed-computing","distributed-systems","embeddings","etl","huggingface","iceberg","machine-learning","multimodal","parquet","python","ray","rust"],"archived":false,"github_pushed_at":"2026-09-17T20:29:06+00:00","maintenance_label":"Very active","stars_delta_30d":130,"url":"https://www.graphcanon.com/tools/eventual-inc-daft","markdown_url":"https://www.graphcanon.com/tools/eventual-inc-daft.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eventual-inc-daft","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eventual-inc-daft"},"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":"ai-engineering","name":"ai-engineering"},{"slug":"ai-pipeline","name":"ai-pipeline"},{"slug":"arrow","name":"arrow"},{"slug":"artificial-intelligence","name":"artificial-intelligence"},{"slug":"big-data","name":"big-data"},{"slug":"data-engineering","name":"data-engineering"},{"slug":"distributed-computing","name":"distributed-computing"},{"slug":"embeddings","name":"embeddings"}],"edges":[],"neighbours":[{"slug":"huggingface-datasets","name":"datasets","tagline":"Largest hub of ready-to-use datasets for AI models","github_url":"https://github.com/huggingface/datasets","owner":"huggingface","repo":"datasets","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":21999,"forks":3448,"topics":["ai","artificial-intelligence","computer-vision","dataset-hub","datasets","deep-learning","huggingface","llm","machine-learning","natural-language-processing","nlp","numpy","pandas","pytorch","speech","tensorflow"],"archived":false,"github_pushed_at":"2026-09-17T10:04:41+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-datasets","markdown_url":"https://www.graphcanon.com/tools/huggingface-datasets.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-datasets","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-datasets","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":["model-training","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":"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":["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":"evolvinglmms-lab-lmms-eval","name":"lmms-eval","tagline":"One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks","github_url":"https://github.com/EvolvingLMMs-Lab/lmms-eval","owner":"EvolvingLMMs-Lab","repo":"lmms-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/154951679?v=4","primary_language":"Python","stars":4368,"forks":639,"topics":["agi","audio-evaluation","benchmark","evaluation","large-language-models","llm-evaluation","multimodal","multimodal-evaluation","video-understanding","vision-language-model","vlm"],"archived":false,"github_pushed_at":"2026-08-06T02:22:23+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval","markdown_url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/evolvinglmms-lab-lmms-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=evolvinglmms-lab-lmms-eval","shared_categories":[]},{"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":"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"]},{"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"]},{"slug":"milvus-io-bootcamp","name":"bootcamp","tagline":"Dealing with all unstructured data including reverse image search, audio search, molecular search, video analysis, and question-answer systems.","github_url":"https://github.com/milvus-io/bootcamp","owner":"milvus-io","repo":"bootcamp","owner_avatar_url":"https://avatars.githubusercontent.com/u/51735404?v=4","primary_language":"Jupyter Notebook","stars":2444,"forks":684,"topics":["audio-search","deep-learning","embeddings","image-classification","image-recognition","image-search","llm","milvus","nlp","python","question-answering","rag","semantic-search","unstructured-data","vector-database"],"archived":false,"github_pushed_at":"2026-09-08T09:14:04+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/milvus-io-bootcamp","markdown_url":"https://www.graphcanon.com/tools/milvus-io-bootcamp.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/milvus-io-bootcamp","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=milvus-io-bootcamp","shared_categories":["data-retrieval"]}]}}