Havuz
Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.
Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.
EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster
Etiketler yükleniyor…
- 101
Pareto-optimal models for cleaning the web — fast, encoder-based main-content extraction from HTML.
0,4/gün ort. +0 son gün — commit HTML 07 Nis 2026 güncellendi 01 Tem 2026 - 102
🛡️ A modern, AI-powered WAF with visual forensic playback via rrweb. Protect your web apps with LLM-driven threat detection, real-time visua
0,3/gün ort. +0 son gün — commit HTML 05 Nis 2026 güncellendi 10 Nis 2026 - 103
A zero-allocation, header-only C++ BPE tokenizer for Qwen, built for maximum inference throughput.
0,1/gün ort. +0 son gün — commit C++ 03 Nis 2026 güncellendi 04 Nis 2026 - 104
A free, open GenAI curriculum built from scratch. Start from zero, build real projects, and work your way up to production AI systems.
0,1/gün ort. +0 son gün — commit Jupyter Notebook 03 Nis 2026 güncellendi 27 gün önce - 105
A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summa
0,1/gün ort. +0 son gün — commit Jupyter Notebook 03 Nis 2026 güncellendi 24 Ağu 2026 - 106
Biologically-grounded adversarial training platform: cyclic Wake/Dream/Nightmare/Compress phases that accumulate model robustness without ca
0,2/gün ort. +0 son gün — commit Python 01 Nis 2026 güncellendi 5 gün önce - 107
Detect hallucinations in LLM responses. Verify every claim against source documents using hybrid STS + NLI. Works with LangChain, LlamaIndex
0,2/gün ort. +0 son gün — commit Python 01 Nis 2026 güncellendi 16 gün önce - 108
A locally-running multi-agent human in the loop system for deep, interdisciplinary research with only 4 dependencies.
0,3/gün ort. +0 son gün — commit Python 31 Mar 2026 güncellendi 07 May 2026 - 109
초경량 한국어 형태소 분석기 — 1MB 모델로 브라우저에서 실행(WASM). Ultra-lightweight Korean morphological analyzer in the browser. npm: garu-ko
0,8/gün ort. +0 son gün — commit TypeScript 27 Mar 2026 güncellendi 5 gün önce - 110
Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.
1,8/gün ort. +0 son gün 0 commit 0 yazar Python 26 Mar 2026 güncellendi 06 Tem 2026 - 111
📚 数千篇 AI、LLM、NLP、CV 顶会论文解读，每篇 5 分钟读懂核心思想。
10/gün ort. +7 son gün 0 commit 0 yazar Python 18 Mar 2026 güncellendi 03 Eki 2026 - 1120,9/gün ort. +0 son gün — commit Python 15 Mar 2026 güncellendi 21 Mar 2026
- 113
中文敏感词/违禁词检测 MCP Server | 支持小红书/抖音/快手/B站 | 风险分级+安全替换建议 | 微信: chenganp | 邮箱: 345048305@qq.com
0,4/gün ort. +0 son gün — commit JavaScript 14 Mar 2026 güncellendi 15 Mar 2026 - 114
a LLM inference engine to run on consumer hardware
0,2/gün ort. +0 son gün — commit Python 14 Mar 2026 güncellendi 15 Nis 2026 - 115
All Jina AI APIs as Unix CLI commands. Search, read, embed, rerank - with pipes.
0,8/gün ort. +0 son gün — commit Python 13 Mar 2026 güncellendi 03 Ağu 2026 - 116
Buddhist Digital Text Platform — 10,500+ texts, 613 sources, trilingual cross-canon, AI Q&A (RAG), knowledge graph, full-text search
1,5/gün ort. +0 son gün — commit Python 10 Mar 2026 güncellendi 2 gün önce - 117
Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat p
1,2/gün ort. +1 son gün — commit Python 09 Mar 2026 güncellendi 25 gün önce - 118
Free, open-source AI writing humanizer and detector. 55 patterns, 5 voices, a 0-100 AI-tell score, and nothing leaves your machine.
1,2/gün ort. +0 son gün — commit JavaScript 06 Mar 2026 güncellendi 06 Eyl 2026 - 119
End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking cur
0,2/gün ort. +0 son gün — commit Python 06 Mar 2026 güncellendi 16 Tem 2026