#deepseek Repositories
328 repositories total
Tutel MoE: Optimized Mixture-of-Experts Library, Supporting GLM/Kimi/GPT/DeepSeek/Qwen with FP8/NVFP4/MXFP4
๐ฅ The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without native web access. Free, no signup, no API key. Ask the web or X, get structured JSON evidence. | ๐ฅ The strongest free web search plugin for DeepSeek Harness: free, no signup, no API key. Add search capabilities to models without web accessโquery the web or X and get structured JSON evidence (search, scraping, citations).
No root or Termux required. Run DeepSeek Harness on your Android phone with a single APK. The engine runs inside the app process ยท Read the screen and operate apps ยท Change system settings ยท Scheduled/conditional automation ยท Optional Shizuku support
GLM-5.3-Flash ร J-Space Capability Realization โ Benchmark Presentation of the J-Space Cognition Suite
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done โ all with a transparent, extensible tool loop.
A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry
Lanpose: Generate images of the communityโs whale-girl model, Dafeiyu, from pose sketches and costume collections. Adjust poses, change outfits, and optionally install it in DeepSeek Harness.
DeepSeek Harness (dsh) In-Depth Guide from 0 to 1: Installation / Plugin Development / Performance Tuning / Real-World Case Studies / Empirical Comparison of Multiple Agents Using the Same Model (Chinese + English PDF)
Transparent Python RAG reference with FAISS + BM25 hybrid retrieval, reranking, Gradio UI, and FastAPI.
Open-source alternative to GrokBot, built on DeepSeek Harness. Build your personal bot team: multiple personal agents with persistent memory, identities, and permissions, extensible through DSH plugins. MIT.
Open-source Windows desktop client and GUI for DeepSeek Harness โ zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.
[dsh] A more powerful visual toolkit designed for text-only models: one-line installation and usage, direct image recognition by pasting images, multi-image Q&A, screenshot-to-frontend UI restoration, and more๏ฝDeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
Official Document Writing Skills | AI Official Document Writing Assistant: Prevents Fabrication, Protects Confidentiality, One-Click Formatting to GB/T 9704, Covers 22 Document Types, Supports Claude Code / Codex / Cursor
Whale โ blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows.
๐ค Automatically collected AI repos, tools, websites, papers & tutorials. Practical AI treasure chest ๐
Token-efficient full Python rebuild of Claude Code. AI coding agent in 310K lines of Python.
Uncensored AI API and browser chat: DeepSeek and GLM models, streaming, Python and TypeScript examples, pricing and setup guides.
๐ฅ๏ธ Agent-project workbench for DeepSeek Harness โ sidebar app drawer + dockable split workspace + a live control room watching every project.
A lightning-fast, cross-platform mobile AI Assistant App built with React Native.
Open-source AI Agent platform for teams. Your agents don't just chat โ they read files, run code, call APIs, and deliver results.
KawaiiGPT โ Open-source LLM gateway accessing DeepSeek, Gemini, and Kimi-K2 through reverse-engineered Pollinations API with no API keys required, built-in prompt injection capabilities for security research, Termux/Linux native support, and Rich console interface
End-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, metering, and full-stack observability. AI quality gating: prompt anchoring, CLIP consistency, AV sync auto-rescue.
Jingjing ยท Let DeepSeek chat with you using your WeChat account (Windows desktop app + WPF launcher). WeChat chatbot powered by DeepSeek/Qwen.
Self-hosted mission control for AI coding agents: run Claude Code, OpenCode, Pi, Codex, and Antigravity & Gemini CLI 24/7, from any device, watch every subagent live
A powerful browser extension that supercharges DeepSeek Chat with custom tooling, persistent memory, and seamless project scaffolding. Generate and download files, run Python in-browser, create PowerPoint and Excel documents, build multi-file projects as ZIP archives, and manage custom skills and characters.
ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloads, seamless closed LLM integration, and offline-first RAG knowledge bases, ARGO becomes a DeepResearch powerhouse for autonomous thinking, task planning, and 100% of your data stays locally. Support Win/Mac/Docker.
โ๏ธA native Android app for ChatGPT, Gemini, Claude, and DeepSeek โ๏ธNative Android app for ChatGPT, Gemini, Claude, and DeepSeek
DeepSeek Harness Mobile is a native mobile client for DeepSeek Harness. It connects to Harness via WebSocket through dsh-plugin-mobile-gateway, bringing workspaces, sessions, real-time responses, and Agent execution traces to iPhone while carrying forward the restrained, clear visual language of DeepSeek WebUI.
DeepSeek Harness Story Creation Plugin: Integrates four visual workspaces for web fiction writing, short dramas and comics, novel-to-game adaptation, and video recaps | DeepSeek Harness plugin for novels, short dramas, games & video recaps
๐๐๐A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.
Coordinate your models from Codex. Plan, delegate, use host tools, and review work across workspaces. Formerly Astra Flash Orchestrator.
Open-source TypeScript terminal coding agent for DeepSeek-V4 โ builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.
DeepSeek Harness Launcher: Manage launch entries, multiple instances, versions, plugins, modpacks, MCP, and skills.
AI Productivity Tool - Free and open source, improve user productivity, and protect privacy and data security. Including but not limited to: built-in local exclusive ChatGPT, DeepSeek, Phi, Qwen and other models, one-click batch intelligent processing of pictures, videos, audio, etc.
What if OpenAI Deep Research and Dify were one platform? OpenAgent โ harness architecture for rapidly building vertical AI agents, with deep reasoning loops, visual workflows, RAG, and A2A delegation.
DeepSeek Harness (dsh) Windows desktop client - bundled Node.js + dsh CLI, one-click launch
Pure Rust + CUDA LLM inference engine โ no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
Cost tracking for DeepSeek Harness: session and model costs, token usage, budgets, provider balances, and coding-plan quotas. Bilingual English/Chinese UI.
A visual, non-linear conversation workspace plugin for DeepSeek Harness; a canvas-based session explorer and branching workspace for DeepSeek Harness.
Exploring white-box AGI architectures: metacognition (self-awareness loop), continual learning (knowledge flywheel), world model (conditional space + semantic spatiotemporal graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.
A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.