24 agents available in the DeepSeek directory
🧰 Multi-provider AI toolkit — 18 modules: Embedding, LLM, RAG, Agent, Vision, TTS, STT, Image Gen, Tool Calling, Structured Output, Smart Router, Failover, and more. One interface, any model.
Zero-cost background coding agent. Watches your files, dreams while you are away, answers what was I working on — 100% local, no cloud, no subscriptions.
A privacy-first, fully local Agentic AI legal assistant. Combines multimodal RAG (DeepSeek-R1 + Llama 3.2 Vision) via Telegram for zero-data-leakage contract analysis.
Memory Efficient Coding Agent ( MECA ) vram < 8GiB wukong is the first MECA-class implementation. Primary target: 4–8GB VRAM via ollama.
Open-source AI agent with brain-inspired long-term memory. Three-path fusion retrieval + hierarchical bubble compaction + surprise detection. Self-hosted, mobile-first PWA.
rowser-based AI coding assistant — zero install, zero deploy, zero config. Agentic loop with 10 tools, 18 skills, and a force-directed Cosmos visualization. Runs entirely client-side.
HexClaw Desktop — 企业级安全个人 AI Agent 桌面客户端。Tauri + Vue 3,本地 Sidecar 零云端依赖,支持 Ollama/OpenAI/Claude/DeepSeek 等多模型,图片视频生成,知识库 RAG,MCP 工具插件,飞书/Telegram/Discord 多平台 IM 接入。
Autonomous AI penetration testing agent for Burp Suite. Agentic pentesting with local/cloud LLMs (Ollama, Gemini, DeepSeek, OpenRouter) via Montoya API.
An autonomous multi-agent orchestration system for Home Assistant. Features local LLM control (Ollama/DeepSeek), & RAG-powered technical knowledge,
IIMS delivers a modern full-stack solution via Spring Boot 3.5 (Java 17) and Vue 3 (TypeScript), featuring RBAC/JWT authentication, Milvus RAG, Spring AI (Ollama/DeepSeek/OpenAI), MyBatis Plus, MySQL, Redis, MinIO, Element Plus, Pinia, Vditor, Mermaid, plus dedicated EAS and DMS modules.
k8s llm agent for planing, monitoring and auto healing of the cluster
ChatMe combines agent-driven AI, cross-platform responsiveness, and voice interaction into a single desktop/web app, empowering developers and users to interact with AI like never before.
A local MCP powered financial analyst agent using the DeepSeek-R1 model via Ollama, utilizing Github Copilot and Python. It analyzes user queries related to stocks and financial data, running entirely offline.
Build Fullstack GenAI apps and AI Agents
Agentic Web Search with Google API is an intelligent assistant that uses Agentic AI and the Google Custom Search API to perform live, deep web searches in response to user queries
Local AI RAG agent built using Langgraph, DeepSeek R1 and Ollama
An AI agent based on the Ollama large model, capable of executing Linux commands through natural language and invoking kernel hooks to delve into the underlying system.
Building AI agents using Python, llama Index and using Gemini Api and Deepseek model.
AingDesk是一款简单好用的AI助手,支持知识库、模型API、分享、联网搜索、智能体,它还在飞快成长中。 AingDesk is a simple and easy-to-use AI assistant that supports knowledge bases, model APIs, sharing, internet search, and intelligent agents. It is still growing rapidly.
Local RAG researcher agent built using Langgraph, DeepSeek R1 and Ollama
Multi-agent orchestration for OllamaJS. Includes TTS synthesis and speech recognition for simplified testing. Connected to telegram bot which support multiple chat sessions
Gen AI, Langchain v1 AI Agents, MCP, MySQL AI Agent, DeepSeek, GPT-OSS Qwen3 LLAMA Agent, Lang Graph, Ollama, KGPTalkie
一款JavaSDK用于快速接入AI大模型应用,整合多平台大模型,如OpenAi、智谱Zhipu(ChatGLM)、深度求索DeepSeek、月之暗面Moonshot(Kimi)、腾讯混元Hunyuan、零一万物(01)等等,提供统一的输入输出(对齐OpenAi)消除差异化,优化函数调用(Tool Call),优化RAG调用、支持向量数据库(Pinecone)、内置联网增强,并且支持JDK1.8,为用户提供快速整合AI的能力。
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