{"data":{"node":{"slug":"argilla-io-distilabel","name":"distilabel","tagline":"Framework for synthetic data and AI feedback pipelines","github_url":"https://github.com/argilla-io/distilabel","owner":"argilla-io","repo":"distilabel","owner_avatar_url":"https://avatars.githubusercontent.com/u/18415507?v=4","primary_language":"Python","stars":3353,"forks":252,"topics":["ai","huggingface","llms","openai","python","rlaif","rlhf","synthetic-data","synthetic-dataset-generation"],"archived":false,"github_pushed_at":"2026-07-27T21:55:31+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/argilla-io-distilabel","markdown_url":"https://www.graphcanon.com/tools/argilla-io-distilabel.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/argilla-io-distilabel","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=argilla-io-distilabel"},"categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"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","name":"ai"},{"slug":"huggingface","name":"huggingface"},{"slug":"llms","name":"llms"},{"slug":"openai","name":"openai"},{"slug":"python","name":"python"},{"slug":"rlaif","name":"rlaif"},{"slug":"rlhf","name":"rlhf"},{"slug":"synthetic-data","name":"synthetic-data"}],"edges":[],"neighbours":[{"slug":"humansignal-label-studio","name":"label-studio","tagline":"A multi-type data labeling and annotation tool","github_url":"https://github.com/HumanSignal/label-studio","owner":"HumanSignal","repo":"label-studio","owner_avatar_url":"https://avatars.githubusercontent.com/u/48309720?v=4","primary_language":"TypeScript","stars":28058,"forks":3658,"topics":["annotation","annotation-tool","annotations","boundingbox","computer-vision","data-labeling","dataset","datasets","deep-learning","image-annotation","image-classification","image-labeling","image-labelling-tool","label-studio","labeling","labeling-tool","mlops","semantic-segmentation","text-annotation","yolo"],"archived":false,"github_pushed_at":"2026-08-14T15:21:23+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/humansignal-label-studio","markdown_url":"https://www.graphcanon.com/tools/humansignal-label-studio.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/humansignal-label-studio","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=humansignal-label-studio","shared_categories":[]},{"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":21791,"forks":3322,"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":"2026-07-30T11:23:49+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":[]},{"slug":"raga-ai-hub-ragaai-catalyst","name":"RagaAI-Catalyst","tagline":"Python SDK for AI agent observability and evaluation","github_url":"https://github.com/raga-ai-hub/RagaAI-Catalyst","owner":"raga-ai-hub","repo":"RagaAI-Catalyst","owner_avatar_url":"https://avatars.githubusercontent.com/u/161833182?v=4","primary_language":"Python","stars":16148,"forks":3565,"topics":["agentic-ai","agentic-ai-development","agentneo","agents","ai-agent-monitoring","ai-application-debugging","ai-evaluation-tools","ai-performance-optimization","ai-tool-interaction-monitoring","llm-testing","llm-tracing","llmops"],"archived":false,"github_pushed_at":"2026-02-11T14:43:33+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/raga-ai-hub-ragaai-catalyst","markdown_url":"https://www.graphcanon.com/tools/raga-ai-hub-ragaai-catalyst.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/raga-ai-hub-ragaai-catalyst","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=raga-ai-hub-ragaai-catalyst","shared_categories":["evaluation-observability"]},{"slug":"voxel51-fiftyone","name":"fiftyone","tagline":"Refine high-quality datasets and visual AI models","github_url":"https://github.com/voxel51/fiftyone","owner":"voxel51","repo":"fiftyone","owner_avatar_url":"https://avatars.githubusercontent.com/u/25984855?v=4","primary_language":"TypeScript","stars":11028,"forks":814,"topics":["active-learning","artificial-intelligence","computer-vision","data-centric-ai","data-cleaning","data-curation","data-quality","data-science","deep-learning","developer-tools","image-classification","machine-learning","object-detection","python","unstructured-data","vector-search","visualization"],"archived":false,"github_pushed_at":"2026-08-22T23:37:21+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/voxel51-fiftyone","markdown_url":"https://www.graphcanon.com/tools/voxel51-fiftyone.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/voxel51-fiftyone","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=voxel51-fiftyone","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":"Active","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":"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":5915,"forks":993,"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","evaluation-observability"]},{"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":"Python","stars":4173,"forks":2075,"topics":["data-science","kubeflow","kubeflow-pipelines","kubernetes","machine-learning","mlops","pipeline"],"archived":false,"github_pushed_at":"2026-08-03T15:35:16+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":"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":3250,"forks":288,"topics":[],"archived":false,"github_pushed_at":"2026-08-06T15:27:26+00:00","maintenance_label":"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":"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":2609,"forks":631,"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":"2026-08-24T06:24:56+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":["evaluation-observability"]},{"slug":"dstackai-dstack","name":"dstack","tagline":"Vendor-agnostic orchestration for AI workloads","github_url":"https://github.com/dstackai/dstack","owner":"dstackai","repo":"dstack","owner_avatar_url":"https://avatars.githubusercontent.com/u/54146142?v=4","primary_language":"Python","stars":2219,"forks":250,"topics":["agent-skills","agentic-orchestration","amd","cloud","containers","docker","fine-tuning","gpu","inference","k8s","kubernetes","llms","machine-learning","nvidia","orchestration","python","slurm","training"],"archived":false,"github_pushed_at":"2026-08-23T13:41:13+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/dstackai-dstack","markdown_url":"https://www.graphcanon.com/tools/dstackai-dstack.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/dstackai-dstack","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=dstackai-dstack","shared_categories":["model-training"]},{"slug":"bespokelabsai-curator","name":"curator","tagline":"Synthetic data curation for post-training and structured data extraction","github_url":"https://github.com/bespokelabsai/curator","owner":"bespokelabsai","repo":"curator","owner_avatar_url":"https://avatars.githubusercontent.com/u/167806754?v=4","primary_language":"Python","stars":1718,"forks":146,"topics":["agents","deep-learning","fine-tuning","instruction-tuning","llm","machine-learning","natural-language-processing","prompt","python","synthetic-data","synthetic-dataset-generation"],"archived":false,"github_pushed_at":"2026-08-07T07:54:05+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/bespokelabsai-curator","markdown_url":"https://www.graphcanon.com/tools/bespokelabsai-curator.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bespokelabsai-curator","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bespokelabsai-curator","shared_categories":["model-training"]},{"slug":"datadreamer-dev-datadreamer","name":"DataDreamer","tagline":"Prompt. Generate Synthetic Data. Train & Align Models.","github_url":"https://github.com/datadreamer-dev/DataDreamer","owner":"datadreamer-dev","repo":"DataDreamer","owner_avatar_url":"https://avatars.githubusercontent.com/u/154913957?v=4","primary_language":"Python","stars":1117,"forks":58,"topics":["alignment","deep-learning","fine-tuning","gpt","instruction-tuning","llm","llmops","llms","machine-learning","natural-language-processing","nlp","nlp-library","openai","python","pytorch","synthetic-data","synthetic-dataset-generation","transformers"],"archived":false,"github_pushed_at":"2025-02-02T21:23:50+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/datadreamer-dev-datadreamer","markdown_url":"https://www.graphcanon.com/tools/datadreamer-dev-datadreamer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/datadreamer-dev-datadreamer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=datadreamer-dev-datadreamer","shared_categories":["model-training"]}]}}