{"data":{"node":{"slug":"shantanu-deshmukh-chunktuner","name":"chunktuner","tagline":"Benchmark and optimize chunking strategies for RAG corpus","github_url":"https://github.com/shantanu-deshmukh/chunktuner","owner":"shantanu-deshmukh","repo":"chunktuner","owner_avatar_url":"https://avatars.githubusercontent.com/u/2664513?v=4","primary_language":"Python","stars":2,"forks":0,"topics":["chunking","embedding","evaluation","langchain","litellm","llamaindex","llm","mcp","optimization","rag","ragas","retrieval","text-splitting","vector-database"],"archived":false,"github_pushed_at":"2026-06-21T06:26:13+00:00","maintenance_label":"Steady","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/shantanu-deshmukh-chunktuner","markdown_url":"https://www.graphcanon.com/tools/shantanu-deshmukh-chunktuner.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/shantanu-deshmukh-chunktuner","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=shantanu-deshmukh-chunktuner"},"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":"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"}],"tags":[{"slug":"chunking","name":"chunking"},{"slug":"embedding","name":"embedding"},{"slug":"evaluation","name":"evaluation"},{"slug":"langchain","name":"langchain"},{"slug":"litellm","name":"litellm"},{"slug":"llamaindex","name":"llamaindex"},{"slug":"llm","name":"llm"},{"slug":"mcp","name":"mcp"}],"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":["evaluation-observability","data-retrieval"]},{"slug":"google-langextract","name":"langextract","tagline":"Python library for extracting structured information from unstructured text using LLMs","github_url":"https://github.com/google/langextract","owner":"google","repo":"langextract","owner_avatar_url":"https://avatars.githubusercontent.com/u/1342004?v=4","primary_language":"Python","stars":38614,"forks":2704,"topics":["gemini","gemini-ai","gemini-api","gemini-flash","gemini-pro","information-extration","large-language-models","llm","nlp","python","structured-data"],"archived":false,"github_pushed_at":"2026-09-13T18:57:36+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/google-langextract","markdown_url":"https://www.graphcanon.com/tools/google-langextract.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/google-langextract","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=google-langextract","shared_categories":["data-retrieval"]},{"slug":"patchy631-ai-engineering-hub","name":"ai-engineering-hub","tagline":"Tutorials on LLMs, RAGs, and real-world AI agent applications","github_url":"https://github.com/patchy631/ai-engineering-hub","owner":"patchy631","repo":"ai-engineering-hub","owner_avatar_url":"https://avatars.githubusercontent.com/u/38653995?v=4","primary_language":"Jupyter Notebook","stars":37020,"forks":6107,"topics":["agents","ai","llms","machine-learning","mcp","rag"],"archived":false,"github_pushed_at":"2026-07-27T18:43:06+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/patchy631-ai-engineering-hub","markdown_url":"https://www.graphcanon.com/tools/patchy631-ai-engineering-hub.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/patchy631-ai-engineering-hub","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=patchy631-ai-engineering-hub","shared_categories":[]},{"slug":"promtengineer-localgpt","name":"localGPT","tagline":"Chat with your documents locally using GPT models","github_url":"https://github.com/PromtEngineer/localGPT","owner":"PromtEngineer","repo":"localGPT","owner_avatar_url":"https://avatars.githubusercontent.com/u/134474669?v=4","primary_language":"Python","stars":22202,"forks":2461,"topics":[],"archived":false,"github_pushed_at":"2026-08-26T04:52:30+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/promtengineer-localgpt","markdown_url":"https://www.graphcanon.com/tools/promtengineer-localgpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/promtengineer-localgpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=promtengineer-localgpt","shared_categories":["data-retrieval"]},{"slug":"arindam200-awesome-ai-apps","name":"awesome-ai-apps","tagline":"A curated list of AI applications showcasing RAG, agents, and workflows.","github_url":"https://github.com/Arindam200/awesome-ai-apps","owner":"Arindam200","repo":"awesome-ai-apps","owner_avatar_url":"https://avatars.githubusercontent.com/u/109217591?v=4","primary_language":"Python","stars":15671,"forks":1802,"topics":["agents","ai","hacktoberfest","llm","mcp"],"archived":false,"github_pushed_at":"2026-09-18T10:01:26+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/arindam200-awesome-ai-apps","markdown_url":"https://www.graphcanon.com/tools/arindam200-awesome-ai-apps.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/arindam200-awesome-ai-apps","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=arindam200-awesome-ai-apps","shared_categories":[]},{"slug":"yusufkaraaslan-skill-seekers","name":"Skill_Seekers","tagline":"Automation tool for converting documentation and code into Claude AI skills","github_url":"https://github.com/yusufkaraaslan/Skill_Seekers","owner":"yusufkaraaslan","repo":"Skill_Seekers","owner_avatar_url":"https://avatars.githubusercontent.com/u/11597362?v=4","primary_language":"Python","stars":15009,"forks":1530,"topics":["ai-tools","ast-parser","automation","claude-ai","claude-skills","code-analysis","conflict-detection","documentation","documentation-generator","github","github-scraper","mcp","mcp-server","multi-source","ocr","pdf","python","web-scraping"],"archived":false,"github_pushed_at":"2026-09-16T20:32:39+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/yusufkaraaslan-skill-seekers","markdown_url":"https://www.graphcanon.com/tools/yusufkaraaslan-skill-seekers.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/yusufkaraaslan-skill-seekers","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=yusufkaraaslan-skill-seekers","shared_categories":[]},{"slug":"rucaibox-llmsurvey","name":"LLMSurvey","tagline":"A collection of papers and resources related to Large Language Models","github_url":"https://github.com/RUCAIBox/LLMSurvey","owner":"RUCAIBox","repo":"LLMSurvey","owner_avatar_url":"https://avatars.githubusercontent.com/u/54706620?v=4","primary_language":"Python","stars":12216,"forks":930,"topics":["chain-of-thought","chatgpt","in-context-learning","instruction-tuning","large-language-models","llm","llms","natural-language-processing","pre-trained-language-models","pre-training","rlhf"],"archived":false,"github_pushed_at":"2025-03-11T09:51:42+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/rucaibox-llmsurvey","markdown_url":"https://www.graphcanon.com/tools/rucaibox-llmsurvey.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rucaibox-llmsurvey","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rucaibox-llmsurvey","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":["data-retrieval"]},{"slug":"run-llama-rags","name":"rags","tagline":"Build ChatGPT over your data with natural language","github_url":"https://github.com/run-llama/rags","owner":"run-llama","repo":"rags","owner_avatar_url":"https://avatars.githubusercontent.com/u/130722866?v=4","primary_language":"Python","stars":6549,"forks":656,"topics":["agent","chatbot","chatgpt","gpts","llamaindex","llm","openai","rag","streamlit"],"archived":false,"github_pushed_at":"2024-04-05T05:36:59+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/run-llama-rags","markdown_url":"https://www.graphcanon.com/tools/run-llama-rags.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/run-llama-rags","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=run-llama-rags","shared_categories":["data-retrieval"]},{"slug":"trigaten-learn-prompting","name":"Learn_Prompting","tagline":"Your Go-To Resource for Mastering Generative AI","github_url":"https://github.com/trigaten/Learn_Prompting","owner":"trigaten","repo":"Learn_Prompting","owner_avatar_url":"https://avatars.githubusercontent.com/u/42948753?v=4","primary_language":"MDX","stars":4726,"forks":668,"topics":["chatgpt","chatgpt-api","deep-learning","gpt-3","gpt-4","gpt-4-api","gpt3","large-language-models","llm","machine-learning","nlp","openai-api","prompt-engineering","prompt-toolkit","prompt-tuning","prompting","transformers"],"archived":false,"github_pushed_at":"2025-01-14T15:04:07+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/trigaten-learn-prompting","markdown_url":"https://www.graphcanon.com/tools/trigaten-learn-prompting.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/trigaten-learn-prompting","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=trigaten-learn-prompting","shared_categories":[]},{"slug":"hegelai-prompttools","name":"prompttools","tagline":"Open-source tools for prompt testing and experimentation","github_url":"https://github.com/hegelai/prompttools","owner":"hegelai","repo":"prompttools","owner_avatar_url":"https://avatars.githubusercontent.com/u/136523567?v=4","primary_language":"Python","stars":3055,"forks":256,"topics":["deep-learning","developer-tools","embeddings","large-language-models","llms","machine-learning","prompt-engineering","python","vector-search"],"archived":false,"github_pushed_at":"2026-02-11T03:24:04+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/hegelai-prompttools","markdown_url":"https://www.graphcanon.com/tools/hegelai-prompttools.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hegelai-prompttools","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hegelai-prompttools","shared_categories":[]},{"slug":"agentset-ai-agentset","name":"agentset","tagline":"The open-source RAG platform with built-in citations and support for deep research","github_url":"https://github.com/agentset-ai/agentset","owner":"agentset-ai","repo":"agentset","owner_avatar_url":"https://avatars.githubusercontent.com/u/200139246?v=4","primary_language":"TypeScript","stars":2092,"forks":187,"topics":["agentic-rag","ai","ai-agents","ai-sdk","chatbots","embeddings","genai","llms","memory","memory-management","rag","vercel-ai-sdk"],"archived":false,"github_pushed_at":"2026-07-16T13:11:34+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/agentset-ai-agentset","markdown_url":"https://www.graphcanon.com/tools/agentset-ai-agentset.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/agentset-ai-agentset","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=agentset-ai-agentset","shared_categories":["data-retrieval"]}]}}