{"data":{"node":{"slug":"maartengr-polyfuzz","name":"PolyFuzz","tagline":"Fuzzy string matching, grouping and evaluation","github_url":"https://github.com/MaartenGr/PolyFuzz","owner":"MaartenGr","repo":"PolyFuzz","owner_avatar_url":"https://avatars.githubusercontent.com/u/25746895?v=4","primary_language":"Python","stars":803,"forks":72,"topics":["bert","edit-distance","embeddings","levenshtein-distance","string-matching","tf-idf"],"archived":false,"github_pushed_at":"2025-07-10T05:10:46+00:00","maintenance_label":"Dormant","stars_delta_30d":3,"url":"https://www.graphcanon.com/tools/maartengr-polyfuzz","markdown_url":"https://www.graphcanon.com/tools/maartengr-polyfuzz.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/maartengr-polyfuzz","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=maartengr-polyfuzz"},"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":"bert","name":"bert"},{"slug":"edit-distance","name":"edit-distance"},{"slug":"embeddings","name":"embeddings"},{"slug":"levenshtein-distance","name":"levenshtein-distance"},{"slug":"string-matching","name":"string-matching"},{"slug":"tf-idf","name":"tf-idf"}],"edges":[],"neighbours":[{"slug":"meilisearch-meilisearch","name":"meilisearch","tagline":"A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.","github_url":"https://github.com/meilisearch/meilisearch","owner":"meilisearch","repo":"meilisearch","owner_avatar_url":"https://avatars.githubusercontent.com/u/43250847?v=4","primary_language":"Rust","stars":59345,"forks":2713,"topics":["ai","api","app-search","database","enterprise-search","faceting","full-text-search","fuzzy-search","geosearch","hybrid-search","instantsearch","search","search-as-you-type","search-engine","semantic-search","site-search","typo-tolerance","vector-database","vector-search","vectors"],"archived":false,"github_pushed_at":"2026-09-17T13:32:29+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/meilisearch-meilisearch","markdown_url":"https://www.graphcanon.com/tools/meilisearch-meilisearch.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/meilisearch-meilisearch","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=meilisearch-meilisearch","shared_categories":["data-retrieval"]},{"slug":"typesense-typesense","name":"typesense","tagline":"Fast, typo tolerant, in-memory fuzzy Search Engine","github_url":"https://github.com/typesense/typesense","owner":"typesense","repo":"typesense","owner_avatar_url":"https://avatars.githubusercontent.com/u/19822348?v=4","primary_language":"C++","stars":26574,"forks":973,"topics":["algolia","datastore","elasticsearch","enterprise-search","faceting","full-text-search","fuzzy-search","geosearch","in-memory","instantsearch","merchandising","pinecone","search","search-engine","semantic-search","similarity-search","site-search","synonyms","typo-tolerance","vector-search"],"archived":false,"github_pushed_at":"2026-09-20T01:42:56+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/typesense-typesense","markdown_url":"https://www.graphcanon.com/tools/typesense-typesense.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/typesense-typesense","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=typesense-typesense","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":"unum-cloud-usearch","name":"USearch","tagline":"Fast Open-Source Search & Clustering engine for Vectors & Arbitrary Objects","github_url":"https://github.com/unum-cloud/USearch","owner":"unum-cloud","repo":"USearch","owner_avatar_url":"https://avatars.githubusercontent.com/u/56397513?v=4","primary_language":"C++","stars":4310,"forks":347,"topics":["approximate-nearest-neighbor-search","clustering","database","faiss","full-text-search","fuzzy-search","image-search","kann","nearest-neighbor-search","recommender-system","search","search-engine","semantic-search","simd","similarity-search","text-search","vector-search","webassembly"],"archived":false,"github_pushed_at":"2026-08-31T22:47:21+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/unum-cloud-usearch","markdown_url":"https://www.graphcanon.com/tools/unum-cloud-usearch.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/unum-cloud-usearch","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=unum-cloud-usearch","shared_categories":[]},{"slug":"nyldn-claude-octopus","name":"claude-octopus","tagline":"Surface AI blindspots before you ship","github_url":"https://github.com/nyldn/claude-octopus","owner":"nyldn","repo":"claude-octopus","owner_avatar_url":"https://avatars.githubusercontent.com/u/4805949?v=4","primary_language":"Shell","stars":4090,"forks":378,"topics":["ai-agents","ai-orchestration","claude-code","claude-code-plugin","codex","copilot","developer-tools","double-diamond","gemini","multi-ai","multi-llm","ollama"],"archived":false,"github_pushed_at":"2026-09-20T05:07:44+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/nyldn-claude-octopus","markdown_url":"https://www.graphcanon.com/tools/nyldn-claude-octopus.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nyldn-claude-octopus","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nyldn-claude-octopus","shared_categories":[]},{"slug":"rashadphz-farfalle","name":"farfalle","tagline":"AI search engine","github_url":"https://github.com/rashadphz/farfalle","owner":"rashadphz","repo":"farfalle","owner_avatar_url":"https://avatars.githubusercontent.com/u/20783686?v=4","primary_language":"TypeScript","stars":3541,"forks":318,"topics":["fastapi","generative-ui","gpt-4o","groq","llm","nextjs","ollama","openai","perplexity","react","search-engine","shadcn-ui","tailwindcss"],"archived":false,"github_pushed_at":"2024-09-27T07:52:45+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/rashadphz-farfalle","markdown_url":"https://www.graphcanon.com/tools/rashadphz-farfalle.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rashadphz-farfalle","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rashadphz-farfalle","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":["data-retrieval"]},{"slug":"run-llama-semtools","name":"semtools","tagline":"Semantic search and document parsing tools for the command line","github_url":"https://github.com/run-llama/semtools","owner":"run-llama","repo":"semtools","owner_avatar_url":"https://avatars.githubusercontent.com/u/130722866?v=4","primary_language":"Rust","stars":1867,"forks":141,"topics":["cli","embeddings","parser","rust","search","semantic","semantic-search","static-embedding"],"archived":false,"github_pushed_at":"2026-03-11T14:30:50+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/run-llama-semtools","markdown_url":"https://www.graphcanon.com/tools/run-llama-semtools.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/run-llama-semtools","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=run-llama-semtools","shared_categories":["data-retrieval"]},{"slug":"ryandonofrio3-osgrep","name":"osgrep","tagline":"Open Source Semantic Search for your AI Agent","github_url":"https://github.com/Ryandonofrio3/osgrep","owner":"Ryandonofrio3","repo":"osgrep","owner_avatar_url":"https://avatars.githubusercontent.com/u/97113725?v=4","primary_language":"TypeScript","stars":1145,"forks":67,"topics":["colbert","embeddings","grep","grep-search"],"archived":false,"github_pushed_at":"2026-01-17T19:45:10+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/ryandonofrio3-osgrep","markdown_url":"https://www.graphcanon.com/tools/ryandonofrio3-osgrep.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ryandonofrio3-osgrep","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ryandonofrio3-osgrep","shared_categories":["data-retrieval"]},{"slug":"dicklesworthstone-swiss-army-llama","name":"swiss_army_llama","tagline":"A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures","github_url":"https://github.com/Dicklesworthstone/swiss_army_llama","owner":"Dicklesworthstone","repo":"swiss_army_llama","owner_avatar_url":"https://avatars.githubusercontent.com/u/35050222?v=4","primary_language":"Python","stars":1055,"forks":67,"topics":["embedding-similarity","embedding-vectors","embeddings","llama2","llamacpp","semantic-search"],"archived":false,"github_pushed_at":"2025-02-27T11:19:55+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/dicklesworthstone-swiss-army-llama","markdown_url":"https://www.graphcanon.com/tools/dicklesworthstone-swiss-army-llama.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/dicklesworthstone-swiss-army-llama","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=dicklesworthstone-swiss-army-llama","shared_categories":["data-retrieval"]},{"slug":"kelindar-search","name":"search","tagline":"Go library for embedded vector search and semantic embeddings with llamacpp","github_url":"https://github.com/kelindar/search","owner":"kelindar","repo":"search","owner_avatar_url":"https://avatars.githubusercontent.com/u/583116?v=4","primary_language":"Go","stars":559,"forks":24,"topics":["ai","bert","embeddings","gguf","gpu","llamacpp","search-engine","semantic-search","simd","vector-search"],"archived":false,"github_pushed_at":"2026-09-19T08:35:34+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/kelindar-search","markdown_url":"https://www.graphcanon.com/tools/kelindar-search.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/kelindar-search","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=kelindar-search","shared_categories":["data-retrieval"]},{"slug":"qdrant-vector-db-benchmark","name":"vector-db-benchmark","tagline":"Framework for benchmarking vector search engines","github_url":"https://github.com/qdrant/vector-db-benchmark","owner":"qdrant","repo":"vector-db-benchmark","owner_avatar_url":"https://avatars.githubusercontent.com/u/73504361?v=4","primary_language":"Python","stars":371,"forks":155,"topics":["benchmark","vector-database","vector-search","vector-search-engine"],"archived":false,"github_pushed_at":"2026-09-18T14:37:44+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/qdrant-vector-db-benchmark","markdown_url":"https://www.graphcanon.com/tools/qdrant-vector-db-benchmark.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/qdrant-vector-db-benchmark","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=qdrant-vector-db-benchmark","shared_categories":[]}]}}