Havuz

yomiyasu, Codex, Claude Code ve Cursor gibi agent ortamlarında AI tarafından üretilen Japonca metinleri daha doğal ve okunabilir kılmaya yönelik bir Agent Skill sunuyor.

Neden yükseliyor · Bir günlük repo yaşına karşılık 625 yıldız, dikkat çekici erken ilgiye işaret ediyor. Ancak bu ilginin kullanıcı benimsemesine dönüşüp dönüşmediği bilinmiyor; son 28 günde 2 commit ve 1 farklı yazar, bakım ve topluluk katkısı için henüz güçlü kanıt oluşturmuyor.

Humanize KR, Korean AI metinlerindeki çeviri kokan ve mekanik ifade kalıplarını tespit edip LLM yardımıyla daha doğal bir üslupla yeniden yazan bir CLI skill’idir.

Neden yükseliyor · 156 günde 5.711 yıldız alması belirgin ilgiye işaret ediyor; son 28 günde 57 commit ve 9 farklı yazar da projenin güncel katkı aldığını gösteriyor. Korean diline odaklanması ve birden fazla CLI ortamını desteklemesi ilgiyi artırmış olabilir; veriler tek başına yükselişin nedenini kanıtlamaz.

AI tarafından üretilen metni LLM yeniden yazımları ve farklı makine çevirisi servisleriyle yeniden yapılandıran, yerelde çalıştırılabilir bir Python pipeline'ıdır.

Neden yükseliyor · 132 günde 2.979 yıldıza ulaşması belirgin ilgiye işaret ediyor; son 28 gündeki 21 commit ve 4 farklı yazar da projenin güncel olarak geliştirildiğini gösteriyor. Bu veriler ilgi ve aktivite kanıtıdır, çıktının kalitesi veya iddia edilen etkinliği için bağımsız kanıt değildir.

📚 数千篇 AI、LLM、NLP、CV 顶会论文解读，每篇 5 分钟读懂核心思想。

IdeaTaste - A benchmark for research taste: let LLM agents propose research ideas, then check how many of them the research area actually we

Classify text in PHP without an LLM bill: typed decisions in 100+ languages, self-hosted. Laravel-ready SDK for Laya, a Jev AI alternative.

High-performance neural networks engine for web, built on top of TypeGPU

Xing4.0-29B-Intent - schema-guided intent recognition and structured information extraction (intent and slot filling, entity, relation and e

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

📚 Read a top-tier AI paper in 5 minutes.

Редактура українського тексту: прибирає сліди ШІ, канцелярит, суржик і кальки, зберігаючи зміст і голос автора. 63 маркери, 30 заборон, скан

Custom APRL machine-learning algorithm + a curated ML knowledge base of 923 papers, lectures, and explainers. NumPy classifier/regressor, te

从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。

Quirón, Claude Code, Codex ve Cursor için metni AI yazım kalıplarına göre düzenleyen ve değişikliği ölçen bir agent skill’idir.

Neden yükseliyor · Beş günlük bir repoda 49 yıldız ve son 28 günde 42 commit dikkat çekiyor. Ancak farklı yazar sayısının 1 olması, aktivitenin tek bir geliştiricide toplandığını gösteriyor; yükselişin nedeni veya kullanıcı benimsemesi hakkında daha güçlü kanıt yok.

Best Open Source NLP LLM Fine-Tuning Trainer Framework 2026

AdalFlow Alternative 2026: Auto-Optimize LLM Apps Without Code

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat p

Runs Hugging Face ONNX models on any Nx backend, with no per-architecture code

211 free visual cards about large language models, from tokenization to deployment. Full collection: 376 cards.

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

Token Cost Parity: Multilingual LLM Efficiency Analysis 2026

The open, machine-readable standard for the Somali language — orthography, grammar, terminology, translation, and AI/benchmark resources, as

AIが書いた日本語を推敲するスキル yomiyasu を、スキルの大きさに上限がある環境向けに短くしたスキル（SKILL.md 18,000字以下）

Train JEV-style System 1 decision models on Qwen3.5 and Qwen3.8-27B: 24-slot decision head, KL distillation, calibration and serving. 在 Qwen

Somali NLP Corpus is an open, high-quality Somali text corpus designed to support research and development in Natural Language Processing (N

Build & Auto-Optimize LLM Apps in 2026: The Ultimate AdalFlow Guide

Master LLM Fine-Tuning Trainer 2026: Advanced NLP Optimization Toolkit

Zero-cost epistemic uncertainty quantification & hallucination detection for LLMs (90,000x faster than Semantic Entropy)

A compounding LLM-wiki, best fit as a personal second brain that organizes and updates itself as it grows, zero upkeep.

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models

Personal academic and research portfolio focused on AI, low-resource Urdu NLP, RAG systems, machine learning, and computer science.

Spectral graph-augmented retrieval for RAG. Augments dense vector search with a weighted chunk graph and its Laplacian spectrum, graph expan

Offline linter that marks LLM-sounding prose. Its statistical model is trained on 2.8B tokens of human text and 11 LLM families, with 0.96 m

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embe

🛡️ A modern, AI-powered WAF with visual forensic playback via rrweb. Protect your web apps with LLM-driven threat detection, real-time visua

SomNLP-Translate is an open, high-quality English–Somali parallel dataset designed to support research and development in machine translatio

日本語の文章から「AI 臭さ」を機械的に拾う Rust 製の Linter

Remove AI text watermarks (SynthID-Text, KGW, Unigram) by regenerating text from its meaning — scheme-blind, runs on local models, every cla

A post-retrieval temporal layer for RAG systems — validity filtering, time decay, document kind classification, and hybrid reranking in one

Wenshu（文枢）— 面向人文社科研究的 AI 知识处理工作流：本地知识库 / RAG / 中文引文 / 理论谱系。AI knowledge workflow for humanities & social sciences: local knowledge base, RAG

Privacy and security guardrails for Spring AI: request-scoped PII tokenization, least-privilege disclosure to tools, and tool authorization

Python SDK for LLM guardrails with safety classification, PII detection, prompt injection defense, and grounding checks. Protect AI applicat

First open-source AI knowledge layer for Togo - 62K+ documents, RAG API, fine-tuned LLM. Built for developers, startups and institutions i

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18

a LLM inference engine to run on consumer hardware

工厂本体驱动的数据问答框架（开源，Apache-2.0）：把中小企业台账/MES/ERP 变成可自然语言问答的语义知识图谱。CSV进答案出，确定性规则引擎+本体GraphRAG+向量混合检索，本地化数据不出厂，换行业只换词典。

LLM-powered conversation summarisation service for OCTO — turns group chats and threads into structured briefs with key decisions, open ques

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking cur

Locally fine-tuned Russian RAG models: document splitter, query expansion, retrieval embedder. Teacher distillation → GGUF → llama.cpp on AM