{"data":{"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":4271,"forks":341,"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":"2026-08-22T19:40:07+00:00","maintenance_label":"Very active","stars_delta_30d":41,"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","description":"Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍","homepage_url":"https://unum.cloud/usearch","license":"Apache-2.0","open_issues":93,"watchers":49,"ai_summary":"Provides fast searching and clustering capabilities for vectors across various programming languages.","readme_excerpt":"# pip install usearch\n\nimport numpy as np\nfrom usearch.index import Index\n\nindex = Index(ndim=3)               # Default settings for 3D vectors\nvector = np.array([0.2, 0.6, 0.4])  # Can be a matrix for batch operations\nindex.add(42, vector)               # Add one or many vectors in parallel\nmatches = index.search(vector, 10)  # Find 10 nearest neighbors\n\nassert matches[0].key == 42\nassert matches[0].distance <= 0.001\nassert np.allclose(index[42], vector, atol=0.1) # Ensure high tolerance in mixed-precision comparisons\n```\n\nMore settings are always available, and the API is designed to be as flexible as possible.\nThe default storage/quantization level is hardware-dependant for efficiency, but `bf16` is recommended for most modern CPUs.\n\n```py\nindex = Index(\n    ndim=3, # Define the number of dimensions in input vectors\n    metric='cos', # Choose 'l2sq', 'ip', 'haversine' or other metric, default = 'cos'\n    dtype='bf16', # Store as 'f64', 'f32', 'bf16', 'f16', 'e5m2', 'e4m3', 'e3m2', 'e2m3', 'u8', 'i8', 'b1'..., default = None\n    connectivity=16, # Optional: Limit number of neighbors per graph node\n    expansion_add=128, # Optional: Control the recall of indexing\n    expansion_search=64, # Optional: Control the quality of the search\n    multi=False, # Optional: Allow multiple vectors per key, default = False\n)\n```","github_created_at":"2023-02-22T09:20:20+00:00","created_at":"2026-07-11T11:33:09.868+00:00","updated_at":"2026-08-23T00:01:13.062088+00:00","categories":[{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"}],"tags":[{"slug":"approximate-nearest-neighbor-search","name":"approximate-nearest-neighbor-search"},{"slug":"clustering","name":"clustering"},{"slug":"database","name":"database"},{"slug":"faiss","name":"faiss"},{"slug":"full-text-search","name":"full-text-search"},{"slug":"fuzzy-search","name":"fuzzy-search"},{"slug":"image-search","name":"image-search"},{"slug":"kann","name":"kann"}],"trust":{"provenance":{"is_fork":false,"github_id":605020435,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-23T00:01:12.287Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":2,"days_since_push":0,"last_release_at":"2026-08-22T19:39:40Z","stars_delta_30d":41,"open_issues_delta_30d":-2},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:33:10.978Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-08-23T00:01:12.736Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-08-23T00:01:12.736Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-23T00:01:12.736Z","managed_saas":false},"languages":{"value":["c++","javascript","typescript","python"],"source":"github.language+package.json+pyproject.toml","observed_at":"2026-08-23T00:01:12.736Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-23T00:01:12.736Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-23T00:01:12.736Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":[],"when_not_to_use":[],"source":"enrich:decision_facts","observed_at":"2026-07-12T14:34:05.564Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"USearch is a fast open-source tool designed for efficient vector and arbitrary object search and clustering across multiple programming languages, backed by the Apache-2.0 license."}]}}