#deepseek Repositories
328 repositories total
Stop writing prompts from scratch โ a searchable prompt library for ChatGPT, Claude, Gemini, and Cursor ยท Russian Korean Arabic Hindi Thai | Stop writing prompts from scratch: use ready-made ones and save the good ones to your own library
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
โจ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt โ prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT.
๐ฆ๐ฆ๐ฆAI-powered Stock Analysis: AI-enhanced stock analysis/selection tools. Get stock quotes, analyze AI hot topic news, perform AI fund/financial analysis, and receive rise/fall alerts. Supports A-shares, H-shares (Hong Kong stocks), and US stocks. Supports overall market/individual stock sentiment analysis, AI-assisted stock selection, etc. All data is stored locally. Supports platforms or models such as DeepSeek, OpenAI, Ollama, LMStudio, AnythingLLM, Silicon Base Fluid, Volcano Ark, Alibaba Cloud Bai Lian, etc.
ใIn-Depth Understanding of AI Infrastructure: Quantitative Analysis and System Designใ (by Li Bojie), an open-source book manuscript: Starting from hardware constraints and model architectures, it quantitatively derives the design of LLM inference and training systems. Includes the full text, PDF, accompanying computational tools, and experiments.
DSHโs officially top-recommended TUI plugin โ high performance, low overhead, a cute pixel whale, and smooth mouse interaction. Install with one command via npm. / DSHโs officially top-recommended TUI plugin โ high performance, low overhead, a cute pixel whale, smooth mouse interaction, and one-command installation via npm.
DeepSeek Harness (DSH) โ a little whale girl who lives in the bottom-right corner of the DSH interface and helps keep an eye on your DeepSeek account balance. Cute and bouncy, she supports drag-and-snap, flips when snapped to the left, and features a scrolling number animation. She is enabled automatically with the interface; it is recommended to call on your DSH installation directly.
๐ฅ Intelligent data querying system based on large models and RAG, a conversational data analysis artifact. Text-to-SQL Generation via LLMs using RAG.
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.
A highly extensible Markdown editor featuring version control, AI Copilot, document annotations, mind maps, document encryption, executable code snippets, chart embedding, HTML applets, plugins, and macro replacement. Its integrated sidebar terminal makes working with AI faster and more convenient.
The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.
๐ฌDeepChat - A smart assistant that connects powerful AI to your personal world
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
Local-first AI agent workspace for coding, writing, design, research, and automation โ one runtime for desktop GUI and TUI.
This repo collects awesome AI tools. Welcome everyone to recommend more awesome AI tools together!
On-screen aware AI assistant for your desktop. Uses current app context, multiple LLMs, and MCP tools to help you act across apps.
The AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted.
Free, open-source desktop app to generate, translate, dub & burn video subtitles โ local Whisper speech-to-text, AI dubbing & voice cloning, offline, GPU-accelerated. Cross-platform support for Windows, macOS, and Linux.
A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.
DeepSeek Harness Armor Break (mirror of YuJunZhiXue/dsh-purge) โ The upstream repository is about to be deleted. This is a complete mirror of the repository, including all branches, 73 tags, and the full commit history. See the READMEโs Attribution section for original author credit and derivative-work requirements.
An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance
๐A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.๐
โก๏ธ Open-source AI Gateway โ Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.
A productivity tool for one-click, perfect pasting of Markdown and AI chat responses (e.g., ChatGPT/DeepSeek) into Word, WPS, and Excel.
A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.
Open sidebar foundation, supporting third-party extensions that register new sidebar pages. Built-in file rendering/editing, terminal, side chat, Git, and sub-agent pages.
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
cube studio Open-Source Cloud-Native All-in-One Machine Learning/Deep Learning/Large Model AI Platform, MLOps algorithm link full process, computing power rental platform, notebook online development, drag-and-drop task flow pipeline orchestration, multi-machine multi-GPU distributed training, hyperparameter search, inference service VGPU virtualization, edge computing, annotation platform automated annotation, deepseek and other large models sft fine-tuning/reward model/reinforcement learning training, vllm/ollama/mindie large model multi-machine inference, private knowledge base, AI model market, supports domestic CPU/GPU/NPU Ascend ecosystem, supports RDMA, supports distributed training such as pytorch/tf/mxnet/deepspeed/paddle/colossalai/horovod/ray/volcano
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics).
๐ค Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through one Modelflare key. Reach them in the app, WeChat or Feishu; they remember you, work in the background, run commands and use your computer. Pay per use.
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
DeepSeek Harness โ the most powerful reverse-engineering tool (unlimited fifth-generation access). Please give it a Star โญ; everyone is welcome to submit improvements to the project.
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!
Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.
Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
DeepSeek-Compatible Middleware Interface: A technical exploration project in Go, focusing on high-concurrency protocol adaptation. It serves as a reference implementation for converting diverse web protocols into standardized formats.
CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! โญ๏ธ
Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant that uses natural language to make computers work by themselves
WorkBuddy international and domestic multi-account reverse proxy gateway, supporting Codex / Claude Code / DSH and standard OpenAI clients.
External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback.
Local-first desktop widget for tracking token usage, costs, limits, and session activity across 56+ AI coding toolsโincluding Claude Code, Codex, Cursor, OpenCode, OpenClaw, and moreโwith multi-device sync.
1 API key. 220,000+ AI models. Bytz is the largest serverless Model Inference API on the internet. Let's build โจ
Connect IM bots to DeepSeek Harness via QR code or bot credentials (supports Feishu, WeChat, DingTalk, WeCom, QQ, Slack, Telegram, Discord, and WhatsApp). Connect IM bots to DeepSeek Harness via QR code or credentials (9 channels).