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

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.

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.

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

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.

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

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

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

Chat with local and cloud AI

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

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

Vela: User Behavior as Supervision Sparks LLM Intelligence — official paper, task templates, and prompts from AllSpark at Xiaohongshu.

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

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

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

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

A recursive self-improvement (RSI) workflow that evolves both target agents (e.g., Pi and DeepSeek Harness) and the RSI system itself.

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

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

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

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

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

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

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

A Large-Scale Knowledge Graph for Automated Scientific Research

Simulate AI Personas in Social Feeds with Real-Time Chat Bots 2026

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

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

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

Daily LLM value rankings - compare 300+ models by intelligence, speed and price. OpenRouter + Artificial Analysis. 大模型性价比排行榜

面向智能座舱的云边协同 AI Agent：端侧毫秒级车控，云端声明式 Multi-Agent 与 Skill/DAG 编排，支持 S2S 实时语音、声纹多用户、HMI和Android双端；LLM 只负责理解与规划，VAL 负责确定性安全执行。

The best model under 200B at near 10 token/s exact batch throughput on a single laptop CPU, with an automatic 8 GB RAM path. Native C, no GP

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

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

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

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

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

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, depl

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.

Benchmarking data agents for verifiable analytics over heterogeneous workspaces.

Production-ready multi-agent platform delivering orchestration, session governance and audit capabilities. Stack: Go/Python/Rust microservic

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

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

Run the native 284B-A13B DeepSeek-V4-Flash-0731 LLM locally on one laptop CPU: pure C, 8 GB RAM minimum, no GPU, best TPOT 0.892 s/token, re

Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tools;

Official implementation of “ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation”

GLM-5.2 NVIDIA NIM Go 客户端 / OpenAI 兼容反向代理 — 自动化 hCaptcha 凭证池 + 流式推理，支持 Docker 部署。Go client & OpenAI-compatible proxy for NVIDIA Playground's

Caveman prompting, measured. A two-channel evaluation framework for prompt compression and LLM token efficiency: what input vs output compre

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

爻枢 Token 智能网关、Token 智能聚合、大模型评测、排名等。关注“爻枢未来”公众号获得更多全自动编程详情。