The Elements of Statistical Learning (ESL)的中文翻译、代码实现及其习题解答。

Makes PDFs look scanned (CLI or in the browser via WASM)

Fast, flexible LLM inference

Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的 Claude Code/Codex 期刊技能…

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

C++ implementations of PP-OCRv3/4/5/6 using ncnn for inference.

Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"

A fast, helpful, and open-source document parser

Yet another coding agent harness, lightweight and written in go.

optimize your documentation through fleets of agents

The Open-Source Elevenlabs alternative AI Voice Clone, Dub, Dictate, Transcribe, Audiobook creator and Voice workflow studio.

Represent large sets and maps compactly with finite state transducers.

Official OCR mini-bench repository for public use. Typescript Version.

LLM speculative inference server for consumer hardware & heterogeneous computing

Generate beautiful dark-themed system architecture diagrams as standalone HTML/SVG files. Works as a Claude AI skill.

Embedding & KV-cache compression for LLMs and vector databases. PCA-Matryoshka + TurboQuant: 27x compression at 99.8% recall@10 (identical reranking). Larger-than-RAM sharded/memmap search, tqp CLI…

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.

The best-benchmarked open-source AI memory system. And it's free.

A ~9M parameter LLM that talks like a small fish.

The agent that grows with you

Most Capable Agent System Prompt

sELF improving agent memory system

Adaptive Test-time Learning and Autonomous Specialization

One file. Your AI coding agent becomes a scientist. 30+ experiments while you sleep.