ollama — 一条命令在本机跑起 Llama、Qwen、DeepSeek 等大模型 · Shelfry
首页 / ollama
ollama Ollama 把本地大模型的下载、运行和 API 服务打包成一条命令。跑 Llama、Qwen、DeepSeek 都只要 ollama run，数据不出本机。
macOS Windows Linux 命令行工具 $ curl -fsSL https://ollama.com/install.sh | sh
Get started You'll be prompted to run a model or connect Ollama to your existing agents or applications such as Claude Code, OpenClaw, OpenCode , Codex, Copilot, and more.
Coding To launch a specific integration:
AI assistant Use OpenClaw to turn Ollama into a personal AI assistant across WhatsApp, Telegram, Slack, Discord, and more:
Chat with a model
REST API Ollama has a REST API for running and managing models.
curl http://localhost:11434/api/chat -d '{
"model": "gemma4",
"messages": [{
"role": "user",
"content": "Why is the sky blue?"
}],
"stream": false
}'
Python from ollama import chat
response = chat(model='gemma4', messages=[
{
'role': 'user',
'content': 'Why is the sky blue?',
},
])
print(response.message.content)
JavaScript import ollama from "ollama";
const response = await ollama.chat({
model: "gemma4",
messages: [{ role: "user", content: "Why is the sky blue?" }],
});
console.log(response.message.content);
Supported backends
llama.cpp project founded by Georgi Gerganov.
Documentation
Community Integrations
Want to add your project? Open a pull request.
Chat Interfaces
Web
Desktop
Dify.AI - LLM app development platformAnythingLLM - All-in-one AI app for Mac, Windows, and LinuxMaid - Cross-platform mobile and desktop clientWitsy - AI desktop app for Mac, Windows, and LinuxCherry Studio - Multi-provider desktop clientOllama App - Multi-platform client for desktop and mobilePyGPT - AI desktop assistant for Linux, Windows, and MacAlpaca - GTK4 client for Linux and macOSSwiftChat - Cross-platform including iOS, Android, and Apple Vision ProEnchanted - Native macOS and iOS clientRWKV-Runner - Multi-model desktop runnerOllama Grid Search - Evaluate and compare modelsmacai - macOS client for Ollama and ChatGPTAI Studio - Multi-provider desktop IDEReins - Parameter tuning and reasoning model supportConfiChat - Privacy-focused with optional encryptionLLocal.in - Electron desktop clientMindMac - AI chat client for MacMsty - Multi-model desktop clientBoltAI for Mac - AI chat client for MacIntelliBar - AI-powered assistant for macOSKerlig AI - AI writing assistant for macOSHillnote - Markdown-first AI workspacePerfect Memory AI - Productivity AI personalized by screen and meeting history
Mobile
SwiftChat, Enchanted, Maid, Ollama App, Reins, and ConfiChat listed above also support mobile platforms.
Code Editors & Development
Libraries & SDKs
Frameworks & Agents
RAG & Knowledge Bases
RAGFlow - RAG engine based on deep document understandingR2R - Open-source RAG engineMaxKB - Ready-to-use RAG chatbotMinima - On-premises or fully local RAGChipper - AI interface with Haystack RAGARGO - RAG and deep research on Mac/Windows/LinuxArchyve - RAG-enabling document libraryCasibase - AI knowledge base with RAG and SSOBrainSoup - Native client with RAG and multi-agent automation
Bots & Messaging
Terminal & CLI
Productivity & Apps
Observability & Monitoring
Opik - Debug, evaluate, and monitor LLM applicationsOpenLIT - OpenTelemetry-native monitoring for Ollama and GPUsLunary - LLM observability with analytics and PII maskingLangfuse - Open source LLM observabilityHoneyHive - AI observability and evaluation for agentsMLflow Tracing - Open source LLM observability
Database & Embeddings
Infrastructure & Deployment
Cloud
Package Managers 核心功能 内容由编辑整理，部分信息来自 GitHub 与项目官网，版权归原作者所有。发现错误？报告问题
信息
分类 未分类
类型 命令行工具
平台 MACOS / WINDOWS / LINUX
协议 MIT
最新版本 v0.40.6
收录时间 2026/10/18 