🏆 #1,398 overall#372 of 1,507 in Search & Retrieval🔥 active this week

NVIDIA /raft

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

$ git clone https://github.com/NVIDIA/raft.git
GitHub social preview for NVIDIA/raft
Stars
1.1K
1,054
This week
+2 ★
Forks
257
257
Language
Cuda
License
Apache-2.0
Created
Jun 13, 2019
7.4 years old
Last push
Nov 16, 2026
🔥 this week

Stars, last 17 days

Oct 28, 2026 → Nov 16, 2026
★ 1K▲ +6★ 1.1K

Categories

GitHub topics

More in Search & Retrieval

Search & Retrieval

NVIDIA/cuvs🔥 active

▲ +8 ★ this week

cuVS - a library for vector search and clustering on the GPU

CudaApache-2.0updated Nov 16, 2026
GitHub ↗★ 898⑂ 266
Search & Retrieval

parthsarthi03/raptor

▲ +10 ★ this week

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

🤖 Language Models
PythonMITupdated Sep 3, 2024
GitHub ↗★ 1.8K⑂ 236
Search & Retrieval

Yomguithereal/talisman🔥 active

▲ +1 ★ this week

Straightforward fuzzy matching, information retrieval and NLP building blocks for JavaScript.

🧠 Natural Language Processing
JavaScriptMITupdated Nov 13, 2026
GitHub ↗★ 734⑂ 50
Search & Retrieval

algorithmfoundry/Foundry

The Cognitive Foundry is an open-source Java library for building intelligent systems using machine learning

JavaOtherupdated May 18, 2021
GitHub ↗★ 135⑂ 39
Search & Retrieval

chrismattmann/tika-similarity

Tika-Similarity uses the Tika-Python package (Python port of Apache Tika) to compute file similarity based on Metadata features.

PythonApache-2.0updated Jun 2, 2026
GitHub ↗★ 107⑂ 60
Search & Retrieval

tao-hpu/cognitive-workspace

🧠 Active memory management system enabling functional infinite context for LLMs through cognitive workspace architecture

🧠 Natural Language Processing
TeXMITupdated Nov 8, 2025
GitHub ↗★ 105⑂ 11

Data from GitHub · snapshot Nov 16, 2026