ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Ollama is an open-source platform that enables developers to run and build applications with large language models locally, including Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, Qwen, and Gemma. It provides a unified interface for integrating AI models into coding workflows, chat applications, and development tools across macOS, Windows, Linux, and Docker environments. Developers can interact with models through a REST API, command-line interface, or native Python and JavaScript libraries, making it straightforward to add AI capabilities to existing applications without cloud dependencies.
Key Features
Use Cases
- 01Integrate local AI code completion and chat into VS Code, Sublime Text, Emacs, or other editors without sending code to external servers
- 02Build RAG (retrieval-augmented generation) applications that combine document knowledge bases with conversational AI
- 03Create chatbots and AI assistants for Discord, Telegram, WhatsApp, Slack, and other messaging platforms
- 04Develop autonomous agents and multi-agent workflows using frameworks like AutoGPT, crewAI, or LangChain
- 05Add AI-powered features to desktop and mobile applications using native Swift, Java, Rust, or .NET SDKs
- 06Run AI models in containerized production environments with the official Docker image and Kubernetes Helm charts
Related Plugins
View moreclaude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
funNLP
funNLP is a comprehensive Chinese natural language Plugin for Claude code
rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
awesome-vue
🎉 A curated list of awesome things related to Vue.js
ollama — FAQ
What is Ollama and what does it do?+
Ollama is a local AI platform that lets you run large language models like Gemma, DeepSeek, Qwen, and others on your own machine. It provides command-line tools, REST APIs, and libraries to integrate these models into applications, coding environments, and agent workflows without relying on cloud services.
How do I install Ollama?+
On macOS and Linux, run 'curl -fsSL https://ollama.com/install.sh | sh' in your terminal. On Windows, execute 'irm https://ollama.com/install.ps1 | iex' in PowerShell. You can also download installers manually from ollama.com/download or pull the official Docker image 'ollama/ollama' from Docker Hub.
Does Ollama work with Claude Code and other AI coding tools?+
Yes, Ollama supports direct integration with Claude Code, Codex, Copilot CLI, DeepSeek Harness, and OpenCode through the 'ollama launch claude' command and similar integrations. It also works with VS Code extensions like Cline and Continue, enabling local AI coding assistance.
Do I need API keys to use Ollama?+
No, Ollama runs models entirely on your local machine and does not require API keys or external authentication. All model inference happens offline after you download models from the Ollama library.
Is Ollama free to use?+
Yes, Ollama is open-source and free to use. The platform, models in the library, and all official SDKs are available at no cost, though you need sufficient local computing resources to run models.
What programming languages does Ollama support?+
Ollama provides official libraries for Python and JavaScript/TypeScript, plus community SDKs for Java, Rust, C++, C#/.NET, Go, Swift, Ruby, R, PHP, Elixir, Dart, and Julia. It also offers a REST API that works with any language capable of making HTTP requests.
How do I install ollama?+
Open the source repository on GitHub and follow its README. ollama is a plugin — MCP Agents Market links you directly to the official repo.
Is ollama free?+
ollama is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.