Havuz

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

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

Fugusashi — Federated Learning of LLM Routing with Human-Interpretable Decisions. Open-source alternative to Sakana AI Fugu.

Meet Reviewer 2 before they meet you ！ A Claude Code skill that red-teams your paper draft — a simulated peer-review panel + an evidence

Open-source, local-first visual ETL and data pipeline builder. Drag-and-drop data prep and ML workflows, preview every step, schedule runs,

面向 AI 奥林匹克与认证（IOAI / NOAI / LMCC）的在线评测与竞赛平台：支持客观题、代码题、LLM 工程题与产物提交（类 Kaggle）评测。

10 legit ways to access major AI models (GPT, Claude, Llama, DeepSeek & more) for FREE — step-by-step guides, no subscription, no card.

End-to-end agentic quantum-ML pipeline: PennyLane GPU quantum-kernel anomaly detection + LangGraph multi-agent system + locally-hosted Qwen3

Mechanical Governance for LLM Decisions — model-agnostic governance regimes (R1/R2/R3), hard gates, entropy commit-reveal and governance met

Open benchmark datasets republished in stressed form to evaluate ML/LLM robustness. Curated by Santander AI Lab.

A dependency-free Python genetic-algorithm engine with pluggable fitness criteria — the reusable search core for an LLM/AI autoresearcher.

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming)

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

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

Combine the results from a panel of models into an enhanced response

Foundational ternary-model inference & training library — CUDA + CPU, BitNet/TQ ternary kernels

Open-source personalized scientific discovery feed powered by arXiv, OpenAlex, PubMed and more.

A complete, structured end-to-end roadmap to become a versatile Generalist AI Engineer from Python/math foundations through ML/DL, CV, NLP,

A fast on device AI image safety detector for React Native / Expo using a CoreML model to detect nudity and unsafe visual content in images.

Ultralytics YOLO26 quickstart for detection, instance and semantic segmentation, depth estimation, classification, pose, OBB, and tracking.

Ultralytics YOLOv8 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

Ultralytics YOLO11 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

Universal local LLM runtime. Drop-in Ollama replacement with HuggingFace integration, pipelines, structured output. Free & open source.

🏆 Real-world problem statements for hackathons & impact projects — curated, structured, and ready to build. 65 problems across 5 tracks: Glo

🥉 3rd Place Hackathon Winner | Solo-built AI platform for detecting, explaining, and mitigating bias in machine learning systems.

Automatically selects diverse photos from Immich as training data for Frigate face recognition

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device inference.

First general Wiki MCP following google's Open Knowledge Format. Let your agent to use, manage, maintain, and health check the wiki (knowled

Open benchmark for expert collapse and routing efficiency in sparse MoE LLMs

Your AI/ML research, on one deck — aggregate arXiv/HF/Semantic Scholar papers, star them, and read in-app with cross-device scroll resume.

A comprehensive hands-on, AI-first Python curriculum with 80+ interactive Jupyter notebooks for AI Engineers from core basics to LLMs, RAG,

Production-grade Machine Learning, Data Science & MLOps skills for AI coding agents (Codex, Claude Code, Cursor, OpenCode). One npx command

Strands-based agents and harnesses for agentic benchmarks.

AI Auto Annotation & YOLO Training Pipeline, End-to-end object detection auto-labeling and YOLO training platform. VLM-powered annotation wi

🔎 Fast, local search across the CS research literature, with an expressive query language, an interactive TUI, and scriptable output.

A TPU you can watch run - real SystemVerilog systolic array, compiled to WASM, visualized live in your browser.

👻 MoEWatch: A lightweight diagnostic and audit library for Mixture-of-Experts (MoE) models in HuggingFace Transformers — the pytest for MoE

开源研究管道 —— 文献综述、新颖性生成、引用验证与对抗性审查 | Open-source research pipeline — literature review, novelty generation, citation verification, and adversar

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

A Django AI library for generating personalized content recommendation feeds based on pgvector.

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

Sleek, mobile-friendly web UI for NVIDIA LocateAnything-3B — open-vocabulary object detection & grounding on your own GPU, via one docker co

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable

OMCBench is a benchmark suite for evaluating malicious-code detection capabilities. The benchmark consists of a labeled set of 800 Python an

Local-first AI creative pipeline for persona-based image/video generation. Identity preservation, visual engines, quality scoring, autopilot