Skip to content

Repository search

Find public projects in our local index, with related guides and tools from MetaCyberGuru. Your search is not sent to GitHub.

Explore topic collections for selection checklists and useful search examples.

Newly discovered sorts by when we first found a repository, not its age, stars or latest push. Refreshing its metadata does not make it new again.

Clear filters

735 matching repositories.

5,477 indexed in total. Latest successful discovery check: 2026-11-08 09:40:22 UTC.

The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.

Language
Python
Licence
Apache-2.0
Stars
10,809
Last push
2026-11-08
First discovered
Last indexed
2026-11-08

cloud-computingcloud-managementcost-optimizationdeep-learningdistributed-traininggpuhyperparameter-tuningjob-queue

Source: GitHub repository metadata.

ChatWeb can crawl web pages, read PDF, DOCX, TXT, and extract the main content, then answer your questions based on the content, or summarize the key points.

Language
Python
Licence
MIT
Stars
916
Last push
2026-05-25
First discovered
Last indexed
2026-11-08

aichatgptcrawlerdocxembeddingfaissgptgpt-35-turbo

Source: GitHub repository metadata.

Learn vector search with Rust and DataFusion; the C++/BusTub track is deprecated.

Language
Rust
Licence
Apache-2.0
Stars
813
Last push
2026-09-16
First discovered
Last indexed
2026-11-08

apache-arrowapproximate-nearest-neighborcoursedatabase-systemsdatafusionhnswivfflatproduct-quantization

Source: GitHub repository metadata.

Simple, Pythonic, text processing--Sentiment analysis, part-of-speech tagging, noun phrase extraction, translation, and more.

Language
Python
Licence
MIT
Stars
9,555
Last push
2026-11-03
First discovered
Last indexed
2026-11-08

natural-language-processingnlpnltkpatternpython

Source: GitHub repository metadata.

High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime

Language
TypeScript
Licence
Not specified
Stars
1,789
Last push
2026-11-06
First discovered
Last indexed
2026-11-08

aicomputer-visionexecutorchllm-inferencemobile-inferenceobject-detectionocron-device-ai

Source: GitHub repository metadata.

⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients.

Language
Python
Licence
Apache-2.0
Stars
1,007
Last push
2025-05-03
First discovered
Last indexed
2026-11-08

agentagentic-aiagentschatbotcomputer-visiondisease-detectiongenaigenai-chatbot

Source: GitHub repository metadata.

A PyTorch-based Speech Toolkit

Language
Python
Licence
Apache-2.0
Stars
11,928
Last push
2026-10-14
First discovered
Last indexed
2026-11-08

asraudioaudio-processingdeep-learninghuggingfacelanguage-modelpytorchspeaker-diarization

Source: GitHub repository metadata.

Add a real-time analytics node to your operational database. Spice is a portable, accelerated SQL query, search, and LLM-inference engine in Rust for data-grounded AI apps and agents.

Language
Rust
Licence
Apache-2.0
Stars
3,130
Last push
2026-11-08
First discovered
Last indexed
2026-11-08

artificial-intelligencedatadata-federationdevelopersfull-text-searchinfrastructurellm-inferencemachine-learning

Source: GitHub repository metadata.

Learn OpenCV : C++ and Python Examples

Language
Jupyter Notebook
Licence
Not specified
Stars
23,238
Last push
2026-11-08
First discovered
Last indexed
2026-11-08

aicomputer-visioncomputervisiondeep-learningdeep-neural-networksdeeplearningmachine-learningopencv

Source: GitHub repository metadata.

The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.

Language
Python
Licence
Apache-2.0
Stars
29,177
Last push
2026-11-07
First discovered
Last indexed
2026-11-08

applicant-tracking-systematshacktoberfestmachine-learningnatural-language-processingnextjspythonresume

Source: GitHub repository metadata.

This repository is a compilation of free resources for learning Data Science.

Language
Not specified
Licence
GPL-3.0
Stars
5,147
Last push
2026-02-01
First discovered
Last indexed
2026-11-08

artificial-intelligencecomputer-visiondata-sciencedatascienceprojectdeeplearningmachine-learningmachine-learning-algorithmsnatural-language-processing

Source: GitHub repository metadata.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Language
Python
Licence
MIT
Stars
31,827
Last push
2025-09-30
First discovered
Last indexed
2026-11-08

agentic-ragdeep-researchemnlp2024knowledge-curationlarge-language-modelsnaaclnlpreport-generation

Source: GitHub repository metadata.

CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.

Language
Java
Licence
GPL-3.0
Stars
10,127
Last push
2026-11-08
First discovered
Last indexed
2026-11-08

named-entity-recognitionnatural-language-processingnlpnlp-parsingstanford-nlp

Source: GitHub repository metadata.

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

Language
Python
Licence
Not specified
Stars
7,908
Last push
2026-11-08
First discovered
Last indexed
2026-11-08

artificial-intelligencecorenlpdeep-learningmachine-learningnamed-entity-recognitionnatural-language-processingnlppython

Source: GitHub repository metadata.

Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀

Language
Rust
Licence
Apache-2.0
Stars
1,323
Last push
2026-10-26
First discovered
Last indexed
2026-11-08

aicloudgenerative-aihacktoberfesthigh-performanceindexinginferenceinformation-retrieval

Source: GitHub repository metadata.

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

Language
Python
Licence
MIT
Stars
13,779
Last push
2026-11-03
First discovered
Last indexed
2026-11-08

aifaissgpt-osslangchainllama-indexllmlocalstorageoffline-first

Source: GitHub repository metadata.

https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

Language
Python
Licence
Apache-2.0
Stars
10,867
Last push
2026-11-05
First discovered
Last indexed
2026-11-08

agentaimemorymultimodalragsearchsearchenginevision

Source: GitHub repository metadata.

Machine Learning Engineering Open Book

Language
Python
Licence
CC-BY-SA-4.0
Stars
19,682
Last push
2026-11-04
First discovered
Last indexed
2026-11-08

aidebugginggpusinferencelarge-language-modelsllmmachine-learningmachine-learning-engineering

Source: GitHub repository metadata.

Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable

Language
Python
Licence
MIT
Stars
1,169
Last push
2026-11-07
First discovered
Last indexed
2026-11-08

apple-siliconiosiphonellama-cppllm-inferencelocal-llmmacosmetal

Source: GitHub repository metadata.

Code for Machine Learning for Trading, 3rd edition — from data sourcing to live execution.

Language
Jupyter Notebook
Licence
MIT
Stars
21,751
Last push
2026-11-06
First discovered
Last indexed
2026-11-08

algorithmic-tradingartificial-intelligencebacktestingdata-sciencedeep-learningfinanceinvestmentinvestment-strategies

Source: GitHub repository metadata.

What this index tells you

We collect selected public repository metadata through GitHub’s official API and store it on our server. This is not a complete index of GitHub. Categories come from discovery queries and topics; a “skills” or “plugins” result is not a verified installation format. We do not run or audit the projects listed here.

Check the original repository’s licence, installation instructions and maintenance history before using it. Stars do not establish security, and a recent push does not prove that a project works. GitHub may have newer information than our last indexed record.

Search is lexical, not an AI answer engine. Short words and spelling differences can affect matches. This site is independent of GitHub. Report a wrong category, stale result or removal request.