{"slug": "ollama-ollama", "title": "ollama/ollama", "summary": "Ollama, the open-source tool for running large language models locally, has released a new version that adds a 'launch' command to connect with AI agents and applications such as Claude Code, Codex, Copilot, and OpenClaw, and introduces support for the Gemma 4 model. The update includes a REST API, Python and JavaScript libraries, and Docker images, enabling developers to integrate open models into their workflows.", "body_md": "Start building with open models.\n\n```\ncurl -fsSL https://ollama.com/install.sh | sh\nirm https://ollama.com/install.ps1 | iex\ncurl -fsSL https://ollama.com/install.sh | sh\n```\n\nThe official [Ollama Docker image](https://hub.docker.com/r/ollama/ollama) `ollama/ollama`\n\nis available on Docker Hub.\n\n```\nollama\n```\n\nYou'll be prompted to run a model or connect Ollama to your existing agents or applications such as `Claude Code`\n\n, `OpenClaw`\n\n, `OpenCode`\n\n, `Codex`\n\n, `Copilot`\n\n, and more.\n\nTo launch a specific integration:\n\n```\nollama launch claude\n```\n\nSupported integrations include [Claude Code](https://docs.ollama.com/integrations/claude-code), [Codex](https://docs.ollama.com/integrations/codex), [Copilot CLI](https://docs.ollama.com/integrations/copilot-cli), [DeepSeek Harness](https://docs.ollama.com/integrations/deepseek-harness), [Droid](https://docs.ollama.com/integrations/droid), and [OpenCode](https://docs.ollama.com/integrations/opencode).\n\nUse [OpenClaw](https://docs.ollama.com/integrations/openclaw) to turn Ollama into a personal AI assistant across WhatsApp, Telegram, Slack, Discord, and more:\n\n```\nollama launch openclaw\n```\n\nRun and chat with [Gemma 4](https://ollama.com/library/gemma4):\n\n```\nollama run gemma4\n```\n\nSee [ollama.com/library](https://ollama.com/library) for the full list.\n\nSee the [quickstart guide](https://docs.ollama.com/quickstart) for more details.\n\nOllama has a REST API for running and managing models.\n\n```\ncurl http://localhost:11434/api/chat -d '{\n  \"model\": \"gemma4\",\n  \"messages\": [{\n    \"role\": \"user\",\n    \"content\": \"Why is the sky blue?\"\n  }],\n  \"stream\": false\n}'\n```\n\nSee the [API documentation](https://docs.ollama.com/api) for all endpoints.\n\n```\npip install ollama\npython\nfrom ollama import chat\n\nresponse = chat(model='gemma4', messages=[\n  {\n    'role': 'user',\n    'content': 'Why is the sky blue?',\n  },\n])\nprint(response.message.content)\nnpm i ollama\npython\nimport ollama from \"ollama\";\n\nconst response = await ollama.chat({\n  model: \"gemma4\",\n  messages: [{ role: \"user\", content: \"Why is the sky blue?\" }],\n});\nconsole.log(response.message.content);\n```\n\n[llama.cpp](https://github.com/ggml-org/llama.cpp)project founded by Georgi Gerganov.\n\nWant to add your project? Open a pull request.\n\n[Open WebUI](https://github.com/open-webui/open-webui)- Extensible, self-hosted AI interface[Onyx](https://github.com/onyx-dot-app/onyx)- Connected AI workspace[LibreChat](https://github.com/danny-avila/LibreChat)- Enhanced ChatGPT clone with multi-provider support[Lobe Chat](https://github.com/lobehub/lobe-chat)- Modern chat framework with plugin ecosystem ([docs](https://lobehub.com/docs/self-hosting/examples/ollama))[NextChat](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web)- Cross-platform ChatGPT UI ([docs](https://docs.nextchat.dev/models/ollama))[Perplexica](https://github.com/ItzCrazyKns/Perplexica)- AI-powered search engine, open-source Perplexity alternative[big-AGI](https://github.com/enricoros/big-AGI)- AI suite for professionals[Lollms WebUI](https://github.com/ParisNeo/lollms-webui)- Multi-model web interface[ChatOllama](https://github.com/sugarforever/chat-ollama)- Chatbot with knowledge bases[Bionic GPT](https://github.com/bionic-gpt/bionic-gpt)- On-premise AI platform[Chatbot UI](https://github.com/ivanfioravanti/chatbot-ollama)- ChatGPT-style web interface[Hollama](https://github.com/fmaclen/hollama)- Minimal web interface[Chatbox](https://github.com/Bin-Huang/Chatbox)- Desktop and web AI client[chat](https://github.com/swuecho/chat)- Chat web app for teams[Ollama RAG Chatbot](https://github.com/datvodinh/rag-chatbot.git)- Chat with multiple PDFs using RAG[Tkinter-based client](https://github.com/chyok/ollama-gui)- Python desktop client\n\n[Dify.AI](https://github.com/langgenius/dify)- LLM app development platform[AnythingLLM](https://github.com/Mintplex-Labs/anything-llm)- All-in-one AI app for Mac, Windows, and Linux[Maid](https://github.com/Mobile-Artificial-Intelligence/maid)- Cross-platform mobile and desktop client[Witsy](https://github.com/nbonamy/witsy)- AI desktop app for Mac, Windows, and Linux[Cherry Studio](https://github.com/kangfenmao/cherry-studio)- Multi-provider desktop client[Ollama App](https://github.com/JHubi1/ollama-app)- Multi-platform client for desktop and mobile[PyGPT](https://github.com/szczyglis-dev/py-gpt)- AI desktop assistant for Linux, Windows, and Mac[Alpaca](https://github.com/Jeffser/Alpaca)- GTK4 client for Linux and macOS[SwiftChat](https://github.com/aws-samples/swift-chat)- Cross-platform including iOS, Android, and Apple Vision Pro[Enchanted](https://github.com/AugustDev/enchanted)- Native macOS and iOS client[RWKV-Runner](https://github.com/josStorer/RWKV-Runner)- Multi-model desktop runner[Ollama Grid Search](https://github.com/dezoito/ollama-grid-search)- Evaluate and compare models[macai](https://github.com/Renset/macai)- macOS client for Ollama and ChatGPT[AI Studio](https://github.com/MindWorkAI/AI-Studio)- Multi-provider desktop IDE[Reins](https://github.com/ibrahimcetin/reins)- Parameter tuning and reasoning model support[ConfiChat](https://github.com/1runeberg/confichat)- Privacy-focused with optional encryption[LLocal.in](https://github.com/kartikm7/llocal)- Electron desktop client[MindMac](https://mindmac.app)- AI chat client for Mac[Msty](https://msty.app)- Multi-model desktop client[BoltAI for Mac](https://boltai.com)- AI chat client for Mac[IntelliBar](https://intellibar.app/)- AI-powered assistant for macOS[Kerlig AI](https://www.kerlig.com/)- AI writing assistant for macOS[Hillnote](https://hillnote.com)- Markdown-first AI workspace[Perfect Memory AI](https://www.perfectmemory.ai/)- Productivity AI personalized by screen and meeting history\n\n[Ollama Android Chat](https://github.com/sunshine0523/OllamaServer)- One-click Ollama on Android\n\nSwiftChat, Enchanted, Maid, Ollama App, Reins, and ConfiChat listed above also support mobile platforms.\n\n[Cline](https://github.com/cline/cline)- VS Code extension for multi-file/whole-repo coding[Continue](https://github.com/continuedev/continue)- Open-source AI code assistant for any IDE[Void](https://github.com/voideditor/void)- Open source AI code editor, Cursor alternative[Copilot for Obsidian](https://github.com/logancyang/obsidian-copilot)- AI assistant for Obsidian[twinny](https://github.com/rjmacarthy/twinny)- Copilot and Copilot chat alternative[gptel Emacs client](https://github.com/karthink/gptel)- LLM client for Emacs[Ollama Copilot](https://github.com/bernardo-bruning/ollama-copilot)- Use Ollama as GitHub Copilot[Obsidian Local GPT](https://github.com/pfrankov/obsidian-local-gpt)- Local AI for Obsidian[Ellama Emacs client](https://github.com/s-kostyaev/ellama)- LLM tool for Emacs[orbiton](https://github.com/xyproto/orbiton)- Config-free text editor with Ollama tab completion[AI ST Completion](https://github.com/yaroslavyaroslav/OpenAI-sublime-text)- Sublime Text 4 AI assistant[VT Code](https://github.com/vinhnx/vtcode)- Rust-based terminal coding agent with Tree-sitter[QodeAssist](https://github.com/Palm1r/QodeAssist)- AI coding assistant for Qt Creator[AI Toolkit for VS Code](https://aka.ms/ai-tooklit/ollama-docs)- Microsoft-official VS Code extension[Open Interpreter](https://docs.openinterpreter.com/language-model-setup/local-models/ollama)- Natural language interface for computers\n\n[LiteLLM](https://github.com/BerriAI/litellm)- Unified API for 100+ LLM providers[Semantic Kernel](https://github.com/microsoft/semantic-kernel/tree/main/python/semantic_kernel/connectors/ai/ollama)- Microsoft AI orchestration SDK[LangChain4j](https://github.com/langchain4j/langchain4j)- Java LangChain ([example](https://github.com/langchain4j/langchain4j-examples/tree/main/ollama-examples/src/main/java))[LangChainGo](https://github.com/tmc/langchaingo/)- Go LangChain ([example](https://github.com/tmc/langchaingo/tree/main/examples/ollama-completion-example))[Spring AI](https://github.com/spring-projects/spring-ai)- Spring framework AI support ([docs](https://docs.spring.io/spring-ai/reference/api/chat/ollama-chat.html))[LangChain](https://python.langchain.com/docs/integrations/chat/ollama/)and[LangChain.js](https://js.langchain.com/docs/integrations/chat/ollama/)with[example](https://js.langchain.com/docs/tutorials/local_rag/)[Ollama for Ruby](https://github.com/crmne/ruby_llm)- Ruby LLM library[any-llm](https://github.com/mozilla-ai/any-llm)- Unified LLM interface by Mozilla[OllamaSharp for .NET](https://github.com/awaescher/OllamaSharp)- .NET SDK[LangChainRust](https://github.com/Abraxas-365/langchain-rust)- Rust LangChain ([example](https://github.com/Abraxas-365/langchain-rust/blob/main/examples/llm_ollama.rs))[Agents-Flex for Java](https://github.com/agents-flex/agents-flex)- Java agent framework ([example](https://github.com/agents-flex/agents-flex/tree/main/agents-flex-llm/agents-flex-llm-ollama/src/test/java/com/agentsflex/llm/ollama))[Elixir LangChain](https://github.com/brainlid/langchain)- Elixir LangChain[Ollama-rs for Rust](https://github.com/pepperoni21/ollama-rs)- Rust SDK[LangChain for .NET](https://github.com/tryAGI/LangChain)- .NET LangChain ([example](https://github.com/tryAGI/LangChain/blob/main/examples/LangChain.Samples.OpenAI/Program.cs))[chromem-go](https://github.com/philippgille/chromem-go)- Go vector database with Ollama embeddings ([example](https://github.com/philippgille/chromem-go/tree/v0.5.0/examples/rag-wikipedia-ollama))[LangChainDart](https://github.com/davidmigloz/langchain_dart)- Dart LangChain[LlmTornado](https://github.com/lofcz/llmtornado)- Unified C# interface for multiple inference APIs[Ollama4j for Java](https://github.com/ollama4j/ollama4j)- Java SDK[Ollama for Laravel](https://github.com/cloudstudio/ollama-laravel)- Laravel integration[Ollama for Swift](https://github.com/mattt/ollama-swift)- Swift SDK[LlamaIndex](https://docs.llamaindex.ai/en/stable/examples/llm/ollama/)and[LlamaIndexTS](https://ts.llamaindex.ai/modules/llms/available_llms/ollama)- Data framework for LLM apps[Haystack](https://github.com/deepset-ai/haystack-integrations/blob/main/integrations/ollama.md)- AI pipeline framework[Firebase Genkit](https://firebase.google.com/docs/genkit/plugins/ollama)- Google AI framework[Ollama-hpp for C++](https://github.com/jmont-dev/ollama-hpp)- C++ SDK[PromptingTools.jl](https://github.com/svilupp/PromptingTools.jl)- Julia LLM toolkit ([example](https://svilupp.github.io/PromptingTools.jl/dev/examples/working_with_ollama))[Ollama for R - rollama](https://github.com/JBGruber/rollama)- R SDK[Portkey](https://portkey.ai/docs/welcome/integration-guides/ollama)- AI gateway[Testcontainers](https://testcontainers.com/modules/ollama/)- Container-based testing[LLPhant](https://github.com/theodo-group/LLPhant?tab=readme-ov-file#ollama)- PHP AI framework\n\n[AutoGPT](https://github.com/Significant-Gravitas/AutoGPT/blob/master/docs/content/platform/ollama.md)- Autonomous AI agent platform[crewAI](https://github.com/crewAIInc/crewAI)- Multi-agent orchestration framework[Strands Agents](https://github.com/strands-agents/sdk-python)- Model-driven agent building by AWS[Cheshire Cat](https://github.com/cheshire-cat-ai/core)- AI assistant framework[any-agent](https://github.com/mozilla-ai/any-agent)- Unified agent framework interface by Mozilla[Stakpak](https://github.com/stakpak/agent)- Open source DevOps agent[Hexabot](https://github.com/hexastack/hexabot)- Conversational AI builder[Neuro SAN](https://github.com/cognizant-ai-lab/neuro-san-studio)- Multi-agent orchestration ([docs](https://github.com/cognizant-ai-lab/neuro-san-studio/blob/main/docs/user_guide.md#ollama))\n\n[RAGFlow](https://github.com/infiniflow/ragflow)- RAG engine based on deep document understanding[R2R](https://github.com/SciPhi-AI/R2R)- Open-source RAG engine[MaxKB](https://github.com/1Panel-dev/MaxKB/)- Ready-to-use RAG chatbot[Minima](https://github.com/dmayboroda/minima)- On-premises or fully local RAG[Chipper](https://github.com/TilmanGriesel/chipper)- AI interface with Haystack RAG[ARGO](https://github.com/xark-argo/argo)- RAG and deep research on Mac/Windows/Linux[Archyve](https://github.com/nickthecook/archyve)- RAG-enabling document library[Casibase](https://casibase.org)- AI knowledge base with RAG and SSO[BrainSoup](https://www.nurgo-software.com/products/brainsoup)- Native client with RAG and multi-agent automation\n\n[LangBot](https://github.com/RockChinQ/LangBot)- Multi-platform messaging bots with agents and RAG[AstrBot](https://github.com/Soulter/AstrBot/)- Multi-platform chatbot with RAG and plugins[Discord-Ollama Chat Bot](https://github.com/kevinthedang/discord-ollama)- TypeScript Discord bot[Ollama Telegram Bot](https://github.com/ruecat/ollama-telegram)- Telegram bot[LLM Telegram Bot](https://github.com/innightwolfsleep/llm_telegram_bot)- Telegram bot for roleplay\n\n[aichat](https://github.com/sigoden/aichat)- All-in-one LLM CLI with Shell Assistant, RAG, and AI tools[oterm](https://github.com/ggozad/oterm)- Terminal client for Ollama[gollama](https://github.com/sammcj/gollama)- Go-based model manager for Ollama[tlm](https://github.com/yusufcanb/tlm)- Local shell copilot[tenere](https://github.com/pythops/tenere)- TUI for LLMs[ParLlama](https://github.com/paulrobello/parllama)- TUI for Ollama[llm-ollama](https://github.com/taketwo/llm-ollama)- Plugin for[Datasette's LLM CLI](https://llm.datasette.io/en/stable/)[ShellOracle](https://github.com/djcopley/ShellOracle)- Shell command suggestions[LLM-X](https://github.com/mrdjohnson/llm-x)- Progressive web app for LLMs[cmdh](https://github.com/pgibler/cmdh)- Natural language to shell commands[VT](https://github.com/vinhnx/vt.ai)- Minimal multimodal AI chat app\n\n[AppFlowy](https://github.com/AppFlowy-IO/AppFlowy)- AI collaborative workspace, self-hostable Notion alternative[Screenpipe](https://github.com/mediar-ai/screenpipe)- 24/7 screen and mic recording with AI-powered search[Vibe](https://github.com/thewh1teagle/vibe)- Transcribe and analyze meetings[Page Assist](https://github.com/n4ze3m/page-assist)- Chrome extension for AI-powered browsing[NativeMind](https://github.com/NativeMindBrowser/NativeMindExtension)- Private, on-device browser AI assistant[Ollama Fortress](https://github.com/ParisNeo/ollama_proxy_server)- Security proxy for Ollama[1Panel](https://github.com/1Panel-dev/1Panel/)- Web-based Linux server management[Writeopia](https://github.com/Writeopia/Writeopia)- Text editor with Ollama integration[QA-Pilot](https://github.com/reid41/QA-Pilot)- GitHub code repository understanding[Raycast extension](https://github.com/MassimilianoPasquini97/raycast_ollama)- Ollama in Raycast[Painting Droid](https://github.com/mateuszmigas/painting-droid)- Painting app with AI integrations[Serene Pub](https://github.com/doolijb/serene-pub)- AI roleplaying app[Mayan EDMS](https://gitlab.com/mayan-edms/mayan-edms)- Document management with Ollama workflows[TagSpaces](https://www.tagspaces.org)- File management with[AI tagging](https://docs.tagspaces.org/ai/)\n\n[Opik](https://www.comet.com/docs/opik/cookbook/ollama)- Debug, evaluate, and monitor LLM applications[OpenLIT](https://github.com/openlit/openlit)- OpenTelemetry-native monitoring for Ollama and GPUs[Lunary](https://lunary.ai/docs/integrations/ollama)- LLM observability with analytics and PII masking[Langfuse](https://langfuse.com/docs/integrations/ollama)- Open source LLM observability[HoneyHive](https://docs.honeyhive.ai/integrations/ollama)- AI observability and evaluation for agents[MLflow Tracing](https://mlflow.org/docs/latest/llms/tracing/index.html#automatic-tracing)- Open source LLM observability\n\n[pgai](https://github.com/timescale/pgai)- PostgreSQL as a vector database ([guide](https://github.com/timescale/pgai/blob/main/docs/vectorizer-quick-start.md))[MindsDB](https://github.com/mindsdb/mindsdb/blob/staging/mindsdb/integrations/handlers/ollama_handler/README.md)- Connect Ollama with 200+ data platforms[chromem-go](https://github.com/philippgille/chromem-go/blob/v0.5.0/embed_ollama.go)- Embeddable vector database for Go ([example](https://github.com/philippgille/chromem-go/tree/v0.5.0/examples/rag-wikipedia-ollama))[Kangaroo](https://github.com/dbkangaroo/kangaroo)- AI-powered SQL client\n\n[Google Cloud](https://cloud.google.com/run/docs/tutorials/gpu-gemma2-with-ollama)[Fly.io](https://fly.io/docs/python/do-more/add-ollama/)[Koyeb](https://www.koyeb.com/deploy/ollama)[Harbor](https://github.com/av/harbor)- Containerized LLM toolkit with Ollama as default backend", "url": "https://wpnews.pro/news/ollama-ollama", "canonical_source": "https://github.com/ollama/ollama", "published_at": "2026-09-03 13:47:48+00:00", "updated_at": "2026-09-03 14:22:38.820124+00:00", "lang": "en", "topics": ["ai-tools", "ai-products", "developer-tools", "large-language-models"], "entities": ["Ollama", "Claude Code", "Codex", "Copilot", "OpenClaw", "Gemma 4", "Docker Hub", "Georgi Gerganov"], "alternates": {"html": "https://wpnews.pro/news/ollama-ollama", "markdown": "https://wpnews.pro/news/ollama-ollama.md", "text": "https://wpnews.pro/news/ollama-ollama.txt", "jsonld": "https://wpnews.pro/news/ollama-ollama.jsonld"}}