Directory
Published directory entries matching your search.
DeepSeek-R1 is the first-generation reasoning model family from DeepSeek, including DeepSeek-R1-Zero and DeepSeek-R1. The repository describes training via large-scale reinforcement learning and cold-start data, and open-sources the models plus six distilled dense models based on Llama and Qwen.
DeepSeek Coder is a series of open code language models trained from scratch on 2T tokens, composed of 87% code and 13% natural language in English and Chinese. Models are offered in 1B, 5.7B, 6.7B and 33B sizes, pre-trained on project-level code corpora with a 16K window size and a fill-in-the-blank task for completion and infilling.
Better DeepSeek is an open-source browser extension that adds tools to the DeepSeek chat interface, including a customizable system prompt, persistent memory, and tag-based output. It can generate downloadable files, PowerPoint and Excel documents, and multi-file ZIP projects, and run Python in the browser. The project is described as unofficial and independent.
A DeepSeek-native terminal coding agent in Rust with OS-level sandboxing, persistent goal mode, background tasks, and verification gates.
DeepSeek-V3 is a Mixture-of-Experts language model with 671B total parameters and 37B activated per token. It uses Multi-head Latent Attention and DeepSeekMoE architectures, was pre-trained on 14.8 trillion tokens, and then underwent supervised fine-tuning and reinforcement learning. The repository provides the model weights and inference code.
DeepSeek-VL2 is a mixture-of-experts vision-language model designed for advanced multimodal understanding. Its public GitHub repository provides documentation including an introduction, release information, model download resources, and a quick start guide.
A curated GitHub list of top AI models and large language models, organized into AI model hosting platforms and top LLMs sections. It includes hosting platforms such as Hugging Face and GitHub Models, and lists models from providers including Meta, Google, Mistral AI and DeepSeek. Contributions are made through pull requests.
Paperless-AI is an automated document analyzer for Paperless-ngx that analyzes and tags documents using OpenAI API, Ollama, Deepseek-r1, Azure and other OpenAI API compatible services. The repository states it is currently not maintained, and notes uncertainty about continuing maintenance.
The official GPT4Free repository, a collection of various powerful language models hosted on GitHub. The repository includes access to models such as opus 4.6, gpt 5.3, kimi 2.5, deepseek v3.2, and gemini 3, and accepts community contributions.
KISS Translator is a simple, open-source bilingual translation extension and userscript. It supports bilingual webpage translation, input-field translation, selection word lookup, and mouse-hover translation, and includes YouTube bilingual subtitles with configurable subtitle styles. It lists built-in services such as Google, Microsoft, Baidu, Tencent, DeepL, OpenAI, Gemini, Claude, Ollama, and DeepSeek. The README notes that provider plugins, Local AI, file translation, and automatic clipboard translation are available only in the Chrome/Edge and Firefox extension builds, not in userscripts and other clients.
Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Moonshot, openclaw / hermes agent, deerflow
supports Telegram, Discord, Slack, Lark（飞书），钉钉, 企业微信, QQ, 微信, compatible with various LLMs including OpenAI, Gemini, DeepSeek, Doubao, and OpenRouter. It offers intelligent conversation, image generation, video creation, and more. Works seamlessly in both private chats and group settings.
Promptfoo is a tool for testing AI prompts, agents and RAG systems. It supports red teaming, penetration testing and vulnerability scanning for AI, enables performance comparison across models including GPT, Claude, Gemini and DeepSeek, uses simple declarative configuration, and integrates with command line and CI/CD workflows.
Repomix is a GitHub-hosted tool that compresses an entire software repository into a single AI-friendly file for use with large language models and other AI tools including Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama and Grok.
