Havuz

A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence

Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi

Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.

A complete, hands-on journey from Python fundamentals to AI Engineering. Explore Data Analytics, Data Science, Machine Learning, Deep Learni

AI Model World, yüzlerce AI modelini fiyat, yetenek, benchmark ve yayın tarihi verileriyle karşılaştıran piksel-art görselli bir web sitesidir.

Neden yükseliyor · Güncel model karşılaştırması ve görsel sunum, hızla değişen AI ekosisteminde ilgi çekici bir kullanım sunuyor. 11 günde 191 yıldız ve son 28 günde 56 commit dikkat çekici bir başlangıç; ancak iki farklı yazar bulunması ve kısa geçmiş, benimsemenin kapsamı ya da sürdürülebilirliği hakkında henüz güçlü kanıt oluşturmuyor.

Halo is an open-source framework built by White Circle for training large language and multimodal models

Chat with local and cloud AI

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

Asking for What Was Never Requested: horizontal and vertical proactivity in LLM agents. Need-graph metrics (no LLM judge) and Q&D, which tra

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

Transformer architecture explained step by step - the full architecture, every attention variant, positional embeddings, and every layer ins

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

An experiment-driven laboratory for understanding LLM sampling strategies. Explore how Temperature, Top-k, and Top-p influence token probabi

NeoHorse, agent iş akışlarında tool use, coding ve yapılandırılmış kararlar için açık ağırlıklı 4B ve 9B modeller sunuyor.

Neden yükseliyor · 23 günde 1.094 yıldıza ulaşmış; son 28 günde 13 commit ve 6 farklı yazar katkısı da projede yakın dönem geliştirme hareketi olduğunu gösteriyor. README'de model yayını ve arXiv teknik raporu duyurulmuş; ancak ilgi ve ekip aktivitesi, modellerin gerçek kullanımını veya bağımsız başarı teyidini tek başına kanıtlamıyor.

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI pe

A Large-Scale Knowledge Graph for Automated Scientific Research

Myrtia — agent-native red teaming for LLMs and AI agents: a deliberating council of attacker models (propose, cross-critique, Borda vote, ch

Observal, ekiplerin coding agent bileşenlerini self-hosted bir registry üzerinden yayımlayıp keşfetmesini ve kullanım verilerini incelemesini sağlayan bir platformdur.

Neden yükseliyor · 181 günlük yaşına karşılık 3.533 yıldız, son 28 günde 84 commit ve 8 farklı yazar dikkat çekiyor; bu, yalnızca README iddiasına değil, yakın dönem geliştirme hareketliliğine de işaret ediyor. Bununla birlikte gerçek kurumsal benimseme veya kullanım hacmi verisi sağlanmadığından ilginin üretim kullanımına dönüştüğü doğrulanamıyor.

Interactive 3D visualization platform for exploring transformer architectures, tensors, and real-time LLM inference.

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

Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.

Benchmark self-evolving Agent upon realistic large-scale file workspaces

An end-to-end framework for Agentic Reinforcement Learning.

[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.

Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.

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。

A pure-Python context management layer for LLM systems — retrieval, re-ranking, memory decay, and token-budget enforcement in one pipeline.

Autonomous AI agent that plays Minecraft on its own — a server-side Fabric mod (MC 1.21.3) where a DeepSeek / OpenAI-compatible LLM drives a

Take the 100 Days of AI challenge - learn one AI concept a day, from machine learning basics to AI agents in production, in 100 days.

A full-screen terminal environment for writing fiction with language models.

Desktop provider manager and local failover router for Codex, Claude Code, and Grok.

Evaan — a fully local, offline-capable AI companion chatbot built with Python & Hugging Face Transformers, running on Qwen2.5-0.5B-Instruct

A user's facts become a few rows in a content-addressed memory table — not a rewrite of the model. Paper, code, data, and interactive site f

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA,

大模型故障 token（glitch token）资料库：收录各 LLM 分词器中已公开记录的异常 token，附异常表现、来源与复现链接。A curated catalog of LLM glitch tokens.

Benchmark for repository-level code understanding: 500 open-ended questions from real GitHub Discussions across 50 repositories, graded by a

Your First LLM-Wiki Conversation Knowledge Base

[ICML 2026] When Drafts Evolve: Speculative Decoding Meets Online Learning

Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"

🌹 Rose: Range-Of-Slice Equilibration PyTorch optimizer. Stateless optimization through range-normalized gradient updates.

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence

TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker

EdGameClaw: Convert any learning material into a game-based course — powered by AI.

[NeurIPS 2026] Official Implementation of "Visual-ERM: Reward Modeling for Visual Equivalence"

a unix-like du command line tool to count token usage per files and directories

hummingbird is a lightweight, zero dependency runtime for massive open source Mixture of Experts (MoE) language models. It unifies SSD, RAM,

VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)