Scalable and memory-optimized training of diffusion models
- ai
- art
- artificial-intelligence
- diffusers
111,810 visible repositories in the index
1,609–1,632 of 2,880 · Most stars
Scalable and memory-optimized training of diffusion models
🦜️🔗LangChain for Rust, the easiest way to write LLM-based programs in Rust
A Toolbox for Adversarial Robustness Research
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
LangChat 是Java&LangChain4j生态的开源 AI Agent 应用平台,支持多模型、Agent、知识库 RAG、Skills、MCP 与智能问数。
让你一眼惊艳的prompt
Break your AI before they do. Join Discord: https://discord.gg/n22d9s3xM
Build your own generative UI chatbot using the Vercel AI SDK and Google Gemini
OpenClaw alternative in your pocket
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
KVMem virtualizes KV memory across inference backends to make ultra-long-context local AI accessible on limited hardware.
把英文论文读成舒服的中文:本地 PDF 论文翻译、原文对照、边读边问 AI、文献管理。Read English papers in comfortable Chinese.
LiveBench: A Challenging, Contamination-Free LLM Benchmark
A commercially-viable ChatGpt web application built with React. 使用React搭建的一款可商业化的ChatGpt Web应用。
使用 PandoraHelper 轻松和你的小伙伴共享 ChatGPT Plus/Claude Pro 服务!
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
Evaluate and improve models and agents using environments
OpenAI Frontier Evals
Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.
The repository host gives no description.
KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)
Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input
High performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.
Neo4j GraphRAG for Python