{"data":{"node":{"slug":"galaxyproject-galaxy","name":"galaxy","tagline":"Data intensive science for everyone","github_url":"https://github.com/galaxyproject/galaxy","owner":"galaxyproject","repo":"galaxy","owner_avatar_url":"https://avatars.githubusercontent.com/u/7937847?v=4","primary_language":"Python","stars":1858,"forks":1170,"topics":["bioinformatics","dna","genomics","hacktoberfest","ngs","pipeline","science","sequencing","usegalaxy","workflow","workflow-engine"],"archived":false,"github_pushed_at":"2026-09-17T02:03:39+00:00","maintenance_label":"Very active","stars_delta_30d":25,"url":"https://www.graphcanon.com/tools/galaxyproject-galaxy","markdown_url":"https://www.graphcanon.com/tools/galaxyproject-galaxy.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/galaxyproject-galaxy","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=galaxyproject-galaxy"},"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":"bioinformatics","name":"bioinformatics"},{"slug":"genomics","name":"genomics"}],"edges":[],"neighbours":[{"slug":"netdata-netdata","name":"netdata","tagline":"The fastest path to AI-powered full stack observability for lean teams","github_url":"https://github.com/netdata/netdata","owner":"netdata","repo":"netdata","owner_avatar_url":"https://avatars.githubusercontent.com/u/43390781?v=4","primary_language":"Go","stars":80598,"forks":6631,"topics":["ai","alerting","cncf","data-visualization","database","devops","docker","grafana","influxdb","kubernetes","linux","machine-learning","mcp","mongodb","monitoring","mysql","netdata","observability","postgresql","prometheus"],"archived":false,"github_pushed_at":"2026-09-20T00:25:10+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/netdata-netdata","markdown_url":"https://www.graphcanon.com/tools/netdata-netdata.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/netdata-netdata","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=netdata-netdata","shared_categories":[]},{"slug":"imbad0202-academic-research-skills-codex","name":"academic-research-skills-codex","tagline":"Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows","github_url":"https://github.com/Imbad0202/academic-research-skills-codex","owner":"Imbad0202","repo":"academic-research-skills-codex","owner_avatar_url":"https://avatars.githubusercontent.com/u/132531341?v=4","primary_language":"Python","stars":11256,"forks":488,"topics":["academic-pipeline","academic-research","academic-writing","ai-research","codex","literature-review","openai-codex","peer-review","prompt-engineering","research-assistant"],"archived":false,"github_pushed_at":"2026-09-16T06:29:53+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/imbad0202-academic-research-skills-codex","markdown_url":"https://www.graphcanon.com/tools/imbad0202-academic-research-skills-codex.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/imbad0202-academic-research-skills-codex","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=imbad0202-academic-research-skills-codex","shared_categories":["developer-tools"]},{"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":"Active","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":"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"]},{"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":6309,"forks":578,"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","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","shared_categories":["model-training","developer-tools"]},{"slug":"huaizhengzhang-ai-infra-from-zero-to-hero","name":"AI-Infra-from-Zero-to-Hero","tagline":"Awesome System for Machine Learning and LLM Infra","github_url":"https://github.com/HuaizhengZhang/AI-Infra-from-Zero-to-Hero","owner":"HuaizhengZhang","repo":"AI-Infra-from-Zero-to-Hero","owner_avatar_url":"https://avatars.githubusercontent.com/u/5894780?v=4","primary_language":null,"stars":4285,"forks":409,"topics":["ai-infra","genai","large-language-models","llmsys","mlsys","model-serving","model-training"],"archived":false,"github_pushed_at":"2025-07-25T02:24:35+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/huaizhengzhang-ai-infra-from-zero-to-hero","markdown_url":"https://www.graphcanon.com/tools/huaizhengzhang-ai-infra-from-zero-to-hero.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huaizhengzhang-ai-infra-from-zero-to-hero","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huaizhengzhang-ai-infra-from-zero-to-hero","shared_categories":["model-training","developer-tools"]},{"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":"Active","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":"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":3324,"forks":297,"topics":[],"archived":false,"github_pushed_at":"2026-08-13T16:04:51+00:00","maintenance_label":"Steady","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":"blazickjp-arxiv-mcp-server","name":"arxiv-mcp-server","tagline":"A Model Context Protocol server for searching and analyzing arXiv papers","github_url":"https://github.com/blazickjp/arxiv-mcp-server","owner":"blazickjp","repo":"arxiv-mcp-server","owner_avatar_url":"https://avatars.githubusercontent.com/u/15390319?v=4","primary_language":"Python","stars":3167,"forks":258,"topics":["ai","arxiv","claude-ai","gpt","llm","mcp-server","model-context-protocol","papers","python","research"],"archived":false,"github_pushed_at":"2026-08-26T23:16:26+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/blazickjp-arxiv-mcp-server","markdown_url":"https://www.graphcanon.com/tools/blazickjp-arxiv-mcp-server.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/blazickjp-arxiv-mcp-server","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=blazickjp-arxiv-mcp-server","shared_categories":[]},{"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":2688,"forks":552,"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":"2026-08-15T00:09:09+00:00","maintenance_label":"Steady","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":"genieincodebottle-generative-ai","name":"generative-ai","tagline":"Comprehensive resources on Generative AI including roadmaps, projects, and interview preparation","github_url":"https://github.com/genieincodebottle/generative-ai","owner":"genieincodebottle","repo":"generative-ai","owner_avatar_url":"https://avatars.githubusercontent.com/u/155415029?v=4","primary_language":"Jupyter Notebook","stars":2640,"forks":636,"topics":["agentic-ai","agentic-framework","claude","gemini","genai","genai-usecase","generative-ai","interview-questions","langchain","langgraph","large-language-model","llm-agent","llm-evaluation","mcp","model-context-protocol","multimodal","n8n","n8n-workflow","openai-api","retrieval-augmented-generation"],"archived":false,"github_pushed_at":"2026-09-13T17:46:14+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/genieincodebottle-generative-ai","markdown_url":"https://www.graphcanon.com/tools/genieincodebottle-generative-ai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/genieincodebottle-generative-ai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=genieincodebottle-generative-ai","shared_categories":[]},{"slug":"nvidia-nemo-curator","name":"Curator","tagline":"Scalable data pre-processing and curation toolkit for LLMs","github_url":"https://github.com/NVIDIA-NeMo/Curator","owner":"NVIDIA-NeMo","repo":"Curator","owner_avatar_url":"https://avatars.githubusercontent.com/u/213689629?v=4","primary_language":"Python","stars":1770,"forks":328,"topics":["data","data-curation","data-prep","data-preparation","data-processing","data-processing-pipelines","data-quality","datacuration","datarecipes","deduplication","fast-data-processing","fine-tuning","large-language-models","large-scale-data-processing","llm","llm-data-quality","llmapps","python","semantic-deduplication"],"archived":false,"github_pushed_at":"2026-09-18T22:03:19+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/nvidia-nemo-curator","markdown_url":"https://www.graphcanon.com/tools/nvidia-nemo-curator.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nvidia-nemo-curator","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nvidia-nemo-curator","shared_categories":["model-training"]}]}}