Benchmarking Generalized Out-of-Distribution Detection
- out-of-distribution-detection
- anomaly-detection
- open-set-recognition
- novelty-detection
140,194 visible repositories in the index
1,801–1,824 of 3,816 · Most stars
Benchmarking Generalized Out-of-Distribution Detection
Run Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime
Open source file-system and knowledge based agent template. Build AI agents that stay up to date with your knowledge base
Codebase for Aria - an Open Multimodal Native MoE
Arena-Hard-Auto: An automatic LLM benchmark.
sentence embedding by Smooth Inverse Frequency weighting scheme
AIConfig is a config-based framework to build generative AI applications.
AutoEvals is a tool for quickly and easily evaluating AI model outputs using best practices.
A series of math-specific large language models of our Qwen2 series.
🩺 首个会看胸部X光片的中文多模态医学大模型 | The first Chinese Medical Multimodal Model that Chest Radiographs Summarization.
[COLM 2025] LIMO: Less is More for Reasoning
A pytorch adversarial library for attack and defense methods on images and graphs
Translated🧬 钝核 (Bluntcore, "blunt core") | Human-AI Intimacy Lab · Bluntcore Intimacy Lab | Human-AI romance, adult AI, Prompt, Memory, Agent, model bed tests, and experiment logs. https://x.com/QloveDudu
TranslatedReverse-proxy AI Studio Playground and Build into an API | AI Studio to OpenAI, Anthropic & Gemini Compatible API
Free Prompts Library | Sabrina Ramonov
AI Agent Evaluator & Red Team Platform
Chat with your documents using local AI
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
React Native binding of llama.cpp
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
Dynamiq is an orchestration framework for agentic AI and LLM applications
A security scanner for your LLM agentic workflows
Local Responses-API shim that exposes Factory BYOK models (and optional ChatGPT GPT-5.5 passthrough) to Codex Desktop.