资产目录

ds4

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Awesome-MCP-ZH

MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients

DeepSeek-LLM

DeepSeek LLM: Let there be answers

DeepSeek-Coder-V2

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

open-multi-agent

Self-hosted TypeScript agent runtime with durable approvals and verifiable run records

paperless-ai

An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compati…

DeepSeek-VL2

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

deepreasoning

A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claud…

train-llm-from-scratch

A straightforward method for training your LLM, from downloading data to generating text

aichat

All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gem…

gpt-load

Self-hosted AI gateway for multi-channel, multi-credential setups — API keys and subscription accounts, scheduling, fail…

tiny-universe

《大模型白盒子构建指南》：一个全手搓的Tiny-Universe

ralphy

My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & Droid in a…

MCP-SuperAssistant

Brings MCP to ChatGPT, DeepSeek, Perplexity, Grok, Gemini, Google AI Studio, OpenRouter, DeepSeek, T3 Chat and more

tokenspeed

TokenSpeed is a speed-of-light LLM inference engine

Qwen3-Embedding

DemoGPT

🤖 Create agentic apps in a second with your prompts

MiniMax-01

The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Att…

Mini-Agent

A minimal yet professional single agent demo project that showcases the core execution pipeline and production-grade fea…

h3.c

MiniMax H3 inference engine for Mac computers