Lists (1)
Sort Name ascending (A-Z)
Stars
Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !
A framework for prompt tuning using Intent-based Prompt Calibration
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
XiaomiMiMo / verl
Forked from verl-project/verlverl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
LLM API 管理 & 分发系统,支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型,统一 API 适配,可用于 key 管理与二次分发。单可执行文件,提供 Docker 镜像,一键部署,开箱即用。LLM API management & k…
A minimal multimodal post-training framework, written from scratch to be read: pretrain, SFT, DPO, GRPO and on-policy distillation in ~1900 lines.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MiniCPM5: SOTA on-device LLMs, small yet powerful.
See, hear, and interact on your local devices.
Open-source framework for the research and development of foundation models.
DeepSeek Harness: Everything is a Plugin.
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
面向开发者与初学者的 nano-vLLM 交互式源码教程 - 通过 13 个 HTML 互动实验 + 13 章中文教程理解大模型推理引擎
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
🐧 Unified and Stable RSI Platform
Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.
Build and run agents you can see, understand and trust.
中文翻译: https://github.com/forrestchang/andrej-karpathy-skills
Task-oriented AI Agent productivity platform
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
Description: Experimental nano-vLLM fork for Qwen3.6 support, CUDA Graph, paged KV cache, and inference-engine learning.
Qwen3.8 is the large language model series developed by Qwen team, Alibaba Group.
One interface for 1,000+ LLMs, with zero-code switching and built-in observability. (GPT 6 / Claude 5 46BC / Gemini 4)
OpenTinker is an RL-as-a-Service infrastructure for foundation models
A framework for efficient model inference with omni-modality models