Deepseek: open-source projects on GitHub
229 repositories on Deepseek, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
Open AI Gateway
A universal open-source gateway for working with 100+ LLMs via any SDK, featuring failover, load balancing, cost control, and full tracing.
★ 3,811 · GoDSH-ANCHORED-STANDARD - QUICK START FULL FUNCTIONALITY
Two‑phase DeepSeek Harness preset: minimal bootstrap load‑up, then the full Standard toolset for high productivity.
★ 3,715 · JavaScriptToken Monitor: Real-Time Tracking
Widget for tracking tokens, costs, and limits of AI tools in real time with cross-device synchronization.
★ 3,701 · JavaScriptArchestra AI: Enterprise Platform
Enterprise AI platform with a guardrails system, MCP registry, gateway, and orchestrator for secure deployment of AI solutions.
★ 3,666 · TypeScriptAI-CHATBOT FOR WEBSITE
Fully customizable AI-chatbot component for your website. Easily integrates and adapts to any tasks.
★ 3,633 · TypeScriptEAC-DESKTOP UNITING DSH PLUGINS
EAC-Desktop unites hundreds of DSH plugins in a single workspace, ensuring their harmonious interaction. Built on TypeScript with DeepSeek Harness, it supports hot reload
★ 3,476 · TypeScriptSURF - PERSONAL AI NOTEBOOK
Surf is an open personal AI notebook: it combines files and web pages, generates notes, and works fully locally.
★ 3,425 · TypeScriptSIDEKICK: LOCAL AI CHAT
Sidekick — native macOS app for chatting with a local LLM, pulling answers from files, folders and web pages. Works fully offline on llama.cpp, no external APIs. Supports
★ 3,324 · SwiftDEEPWIKI-RS: QUICK DOCUMENTATION
Turn code into clear documentation in minutes with the Rust‑tool deepwiki-rs. Perfect for teams and AI agents.
★ 3,174 · RustCHITU: ACCELERATING LLMS IN PYTHON
High-performance framework for fast inference of large language models in Python. Provides flexibility, efficiency, and ease of deployment.
★ 3,123 · PythonJ-SPACE COGNITIVE SUITE
J-Space Cognition Suite — tools for managing model output during inference: deep reasoning, long-horizon tasks, verification and recovery. Based on J-space research from
★ 2,958 · PythonDeepSeek Reasonix: Terminal AI Agent
Terminal AI coding agent based on DeepSeek. Optimized for stable operation with prefix cache — just run and forget.
★ 2,889 · TypeScriptEPHEMERAL WORKSPACES WITH SHARED HISTORY
LayerFS gives each agent a full writable FS over shared history without copying the base. Agents work in parallel, commit changes as deduplicated checkpoints, then branch
★ 2,777 · RustMAID: MANAGE AI MODELS
Free tool for working with local and remote LLMs: llama.cpp, Anthropic, DeepSeek, etc.
★ 2,776 · TypeScriptPAPERSGPT — AI for Zotero
Powerful AI plugin for Zotero with support for ChatGPT, Gemini, Claude, DeepSeek and other models. 2459 stars!
★ 2,709 · JavaScriptLocal AI Novel Writer
Free, open-source novel writing app with AI-assisted outlining, drafting, and editing. Runs locally with user-configured models.
★ 2,635 · TypeScriptPANWATCH: AI AGENT FOR STOCK
PanWatch - self-hosted AI platform for monitoring A-share, HK and US stocks with TradingAgents.On Python 1.8k ★
★ 2,507 · PythonMAXTEXT JAX LLM
Simple, fast, and scalable framework for large language models on JAX and Python.
★ 2,309 · PythonGPT‑5.6 CLAUDE GROK DEEPSEEK PROMPT WORKBENCH
ColdBrew Zero — environment for creating and testing prompts for GPT‑5.6, Claude, Grok and DeepSeek V4 Pro. Assembles instructions from «breakline» blocks, checks their e
★ 2,231 · JavaScriptFast Local AI Engine
Rapid-MLX is the fastest local AI engine for Apple Silicon, running 4.2× faster than Ollama and providing a cached first-token time of just 0.08s.
★ 2,185 · PythonAI CHATBOT FRAMEWORK ON PYTHON
Framework for creating chatbots with NLU and AI on Python. Supports LLM integration and provides a ready-made dialog manager. Actively developed, already 2166 stars on Gi
★ 2,182 · TypeScriptLOU SHANG - AI CODING AGENT
A universal AI agent on Python that combines multiple LLMs and tools for automating coding.
★ 2,091 · PythonFAST LLM LAUNCH ON NPU
FastFlowLM runs LLMs on AMD Ryzen AI NPU in minutes, delivering performance comparable to Ollama but optimized for NPU.
★ 2,050 · C++AI-ASSISTANT PY-GPT FOR EVERYONE
Desktop AI Assistant based on multiple models: GPT-5, GPT-4, Gemini and others, with voice, vision, RAG, and image generation.
★ 2,027 · PythonLOCAL OPEN-SOURCE AI AGENT
Atomic-Chat is a private AI engine for running LLM locally without internet, fully offline on your computer. ⭐ 967 stars on GitHub.
★ 2,008 · TypeScriptAPIPARK AI GATEWAY NEW GENERATION
APIPark — gateway for all models: single entry, LLM request management, load balancing and failover. Supports OpenAI, Claude, Gemini, DeepSeek and more, giving unified re
★ 1,826 · TypeScriptZENFEED: AI TURNS RSS INTO NEWS
zenfeed uses AI to generate personalized RSS feeds, turning any sources into smart news streams.
★ 1,722 · GoCYBERPUNK AI AGENT FOR WINDOWS
Capri is a cyberpunk AI agent for Windows with voice and screen control. Supports Claude Code, Ollama, DeepSeek, Discord calls and desktop automation. 761 stars on GitHub
★ 1,716 · PythonAGENTLY: SIMPLIFYING GEN-AI DEVELOPMENT
Agently — a Python framework for rapid creation of GenAI applications: simple code, event-driven flow, and easy model swapping.
★ 1,584 · PythonTUYAOPEN – AI+IoT FRAMEWORK IN C
TuyaOpen is a framework for rapid integration of AI agents with IoT devices on T2/T3/T5AI and ESP32 platforms, written in C.
★ 1,579 · CIMAGE GENERATION IN DEEPSEEK HARNESS
dsh-image-gen — a plugin for DeepSeek Harness that generates images from text prompts directly in the chat. Written in TypeScript, it supports style and parameter configu
★ 1,546 · TypeScripttt-metal - Metallic Operations Library
TT-NN operator library and low-level programming model for TT-Metalium kernels to accelerate AI workloads on proprietary hardware.
★ 1,505 · C++LUA N1AO AGENT: AI-PENTEST
An autonomous AI agent for system penetration, using a dual reasoning graph. Developed by Professor Lu Hui's team from Guangzhou.
★ 1,476 · PythonFAST LLM ON AMD
Run LLM on AMD Ryzen™ AI in minutes. Like Ollama, but deeply optimized for AMD chips! C++
★ 1,464 · C++GENERATIVE_AI_WITH_LANGCHAIN - BUILD PRODUCTION LLM
Notebooks for creating production-ready LLM applications and agents using LangChain and LangGraph. Practical examples from the generative AI book.
★ 1,459 · Jupyter NotebookAI Workspace for Authors
Smart workspace for content creators: write, research, manage prompts and knowledge base — all in one place with support for multiple AI models.
★ 1,418 · TypeScriptawesome-deepseek-harness - SPEEDING WORK WITH DEEPSEEK
Ecosystem of plugins and tools for DeepSeek Harness: ready-made solutions from dsh-external/hub and the public topic dsh-plugin.
★ 1,370 · PythonOpenMed AI for Healthcare
OpenMed is an open-source Python project using AI for medical data analysis and clinical decision support.
★ 1,365 · PythonPARALLAX: BUILD AI CLUSTER
Parallax lets you quickly deploy a distributed inference service on any infrastructure.
★ 1,301 · PythonBUILD YOUR AI CHAT FOR ANDROID
gpt_multi — a lightweight client for OpenAI, Anthropic, Google, and Ollama. One chat, multiple models, your keys.
★ 1,273 · KotlinVisual Toolkit for LLM
A library for text models that lets them 'see' images: recognize content, answer questions, restore UI, automate GUI, and integrate with agents.
★ 1,262 · PythonANGELSLIM: COMPRESSING MODELS WITHOUT LOSS
A tool for model compression focusing on convenience and efficiency. 1257 stars on GitHub.
★ 1,257 · PythonRUN 284B LLM ON CPU WITHOUT GPU
llama-modchip runs DeepSeek-V4-Flash 284B on pure 64GB CPU RAM: 44.4 tok/s prefill, 9-14 tok/s generation. 30B MoE models up to 111 tok/s. 256K context, Claude Code resto
★ 1,234 · PythonKNOWNOTE: LOCAL AI KNOWLEDGE BASE...
KnowNote — local AI knowledge base on Electron, replacing NotebookLM... Indexes files, answers questions and builds chains of thought without sending data to the cloud.
★ 1,170 · TypeScriptTUTEL ACCELERATES MOE IN C
Optimized Mixture-of-Experts library for accelerated LLM inference with FP8, NVFP4, and MXFP4 support.
★ 1,028 · CGLM-5.3 FLASH AND J-SPACE BENCHMARK
The project shows integration of GLM-5.3 Flash with J-Space for full benchmarking the J-Space Cognition Suite. Results show agent skills implementation and baseline compa
★ 1,016CODEAGENT: AI AGENT FOR TERMINAL
CodeAgent — open-source AI agent working in the terminal. It analyzes the repo, plans changes, edits files, runs tests and repeats the loop until the task is done.
★ 1,012 · PythonPHI — UNIVERSAL AI CODER
PHI is a universal AI coding agent. Supports infinite LLM providers, sub-agents, and hashline edits. Permission gate controls file and command access.
★ 1,004 · GoDSCODE AI AGENT CODING
DSCODE provides a persistent shell with Ultra subagents, auto‑approval of changes and Chrome MCP integration. The system collects session telemetry to analyse coding‑agen
★ 1,001 · JavaScriptMODSEARCH - COMPLETELY FREE SEARCH
modsearch is a free web‑search plugin for DeepSeek Harness that lets any LLM obtain structured JSON data from the web and X without registration or an API key.
★ 989 · TypeScriptLOCAL_PDF_CHAT_RAG - PDF CHAT RAG
A simple Python RAG with hybrid FAISS+BM25 search, reranking, and a Gradio + FastAPI UI.
★ 961 · PythonHexabot v3 AI platform
Hexabot v3 combines workflows, actions, agents, and conversational channels in a single environment for automating AI tasks.
★ 952 · TypeScriptDSH Vision Toolkit
The project provides a powerful toolkit for working with images in pure text models: simple installation, recognition of inserted images, multi‑image Q&A, UI recovery fro
★ 945 · TypeScriptUltra-fast engine
Ultra-fast LLM inference engine in Python with maximum performance. 943 stars on GitHub.
★ 943 · PythonMACAI: AI CHAT FOR macOS
A native macOS app that unifies chat with any AI providers in a single interface.
★ 942 · SwiftAIDERMACS: AI PARTNER IN EMacs
The AiderMacs plugin integrates the Aider AI assistant into Emacs, providing instant code suggestions and refactoring directly in the buffer.
★ 936 · Emacs LispWHALE FAST AI AGENT
Whale is a terminal AI agent in Go for DeepSeek: 98% cache hits, 1M context, MCP tools, and dynamic workflows.
★ 935 · GoDEEPSEEK HARNESS DESKTOP CLIENT
Open-source Windows client for DeepSeek Harness with zero‑setup installation. Includes Codex, plugins, skills, SSH, mobile remote access and 11 UI skins. Written in TypeS
★ 934 · TypeScriptINCARNAMIND AI CHAT WITH DOCUMENTS
Free desktop app for macOS, Windows and Linux, allowing you to ask questions about your documents and get answers with exact page links. IncarnaMind verifies each citatio
★ 858 · TypeScriptPERSONAL AI AGENT TEAM
Open-source GrokBot alternative on DeepSeek Harness. Creates bot team with persistent memory, identities and permissions. Extensible via DSH plugins.
★ 851 · TypeScriptNew projects on this topic in Telegram
Telegram →