a list of tools and frameworks you can use with Ollama
inspired by Awesome Python
| Name/Link | Description | Install | License |
|---|---|---|---|
| Claude Code | Agentic coding tool by Anthropic | Download | Proprietary |
| Cline CLI | Autonomous coding agent for the terminal | npm | Apache-2.0 |
| Codex App | OpenAI desktop coding agent | Download | Proprietary |
| Codex CLI | OpenAI terminal coding agent | npm | Proprietary |
| Copilot CLI | GitHub AI coding agent for the terminal | npm | Proprietary |
| Goose | Desktop coding agent by Block | Download | Apache-2.0 |
| Lifeboat | Coding agent failover: drops to a local model on rate limit, ban or outage, carrying your context | Source | MIT |
| memcode | Terminal coding agent with persistent repo memory | Download | MIT |
| Oh My Pi | Terminal coding agent with IDE-style tools | Download | Proprietary |
| omnexx | Long-running terminal coding agent that commits only what passes tests | npm | MIT |
| OpenCode | Open-source terminal coding assistant | npm | MIT |
| POK-Agent | Windows computer-use and coding agent that turns repeated tasks into replayable skills | Download | Apache-2.0 |
| vixl | Local-first desktop coding agent with BYOK and MCP | Download | MIT |
| Name/Link | Description | Install | License |
|---|---|---|---|
| Amica | Open-source interface for interactive 3D characters with voice synthesis and speech recognition | npm | MIT |
| Cheshire Cat assistant framework | Extensible open-source AI agent framework | Docker | GPL-3.0 |
| CorvinOS | Agentic OS connecting Ollama to Discord, Telegram, WhatsApp, Slack and email | pip | Apache-2.0 |
| CrustAI | Local-first assistant with Telegram, WhatsApp, Discord and Slack integration, no cloud | Docker, npm | MIT |
| digibuddy | Desktop pet that wanders your screen and chats with a local LLM | Download | MIT |
| Hermes Agent | Self-improving AI agent by Nous Research | Download | MIT |
| Hermes Desktop | Native AI assistant app by Nous Research | Download | Proprietary |
| Hivekeep | Self-hosted platform running a team of specialized AI agents with persistent memory and a web UI | Docker | MIT |
| LobeHub | Chief Agent Operator for 7×24 AI team orchestration | Download | Custom |
| OpenClaw | Personal AI assistant for your devices | Download | MIT |
| Talos | Permission-gated agent where every tool call passes a deterministic policy kernel with an audit log | Download | MIT |
| Name/Link | Description | Install | License |
|---|---|---|---|
| Cline | VS Code coding assistant | Marketplace | Apache-2.0 |
| JetBrains | JetBrains IDE AI integration | Download | Proprietary |
| MindMac | Native macOS ChatGPT client with inline mode and prompt templates | Download | Proprietary |
| VS Code | VS Code with Copilot Chat + Ollama | Download | MIT |
| Xcode | Xcode AI integration | Download | Proprietary |
| Zed | Zed editor AI integration | Download | Apache-2.0 |
| Name/Link | Description | Install | License |
|---|---|---|---|
| big-AGI | AI suite with personas, multi-model chats, and code execution | npm | MIT |
| BionicGPT | On-premise ChatGPT alternative with data confidentiality | Docker, Download | Apache-2.0 |
| CapyBro | Windows global-hotkey text rewriting via local models | Download | MIT |
| chat: chat web app for teams | Chat web app for teams with user management and rate limits | Docker | MIT |
| Chatbox | Desktop and mobile AI chat client | Download | GPL-3.0 |
| ChatOllama | Open-source AI chatbot for private language model chat | npm | Custom |
| GClaude Indexer | Turns a folder of scanned documents into a searchable index and timeline, offline | pip | GPL-3.0 |
| GramVault | Private RAG chat over your saved Instagram content, with citations | pip, npm | MIT |
| HammerAI | Offline AI character chat powered by Ollama and Llama.cpp | Download | Proprietary |
| HTML UI | Simple HTML UI for Ollama | Download, Browser extension | MIT |
| JoeBro | Native macOS AI workspace with chat, documents, memory and MCP tools | Download | GPL-3.0 |
| LibreChat | Multi-provider ChatGPT clone with agents, MCP, and presets | Docker, npm | MIT |
| LLM-X | Local LLM web UI that runs in the browser | Download, npm | MIT |
| Local Deep Research | Deep research with local RAG across arXiv, PubMed and the web | Docker, pip | MIT |
| Lollms-Webui | Web UI for local and remote LLMs with multimodal features | Download | Apache-2.0 |
| Minimalistic React UI for Ollama Models | Minimalistic offline UI for Ollama LMs | npm | MIT |
| Msty | Private AI workspace and autonomous AI agent platform | Download | Proprietary |
| Nosia | Self-hosted AI RAG + MCP platform | Docker | MIT |
| Off Grid AI Desktop | Local-first macOS AI suite with chat, image generation, dictation and memory/RAG | Download | AGPL-3.0 |
| Ollama Client | Browser sidepanel for local model chat with RAG, web search and page context | Browser extension | MIT |
| Ollama RAG Chatbot | Chat with multiple PDFs locally | Docker | Apache-2.0 |
| Onyx | Self-hostable Chat UI for Ollama | Docker | Custom |
| Open Webui | User-friendly web interface with chat, RAG and model management | Docker, npm | Custom |
| RAGFlow | Open-source RAG engine with agentic retrieval | Docker | Apache-2.0 |
| Second Brain | Local-first knowledge base CLI with hybrid and GraphRAG search, plus MCP server | pip, Docker | MIT |
| ThoughtDAG | Visual LLM workspace where graph edges control which nodes enter model context | npm | MIT |
| Typescript UI | TypeScript web GUI for Ollama | npm | MIT |
| Name/Link | Description | Install | License |
|---|---|---|---|
| Conduck | Native Apple apps for self-hosted AI, voice and text | Download | Apache-2.0 |
| Enchanted | Native macOS and iOS app | Download | Apache-2.0 |
| Maid | Cross-platform Flutter app for local llama.cpp and remote Ollama, OpenAI and Mistral models | Download | MIT |
| Name/Link | Description | Install | License |
|---|---|---|---|
| AmicoScript | Local audio and video transcription with speaker diarization, search and LLM summaries | pip, Docker | MIT |
| Dify.AI | Production-ready platform for agentic workflow development | Download, Docker | Custom |
| iscooked | Security scanner for Ollama and local AI setups: network exposure, API auth, file permissions | Source | MIT |
| LocoPilot | Vision, browser and desktop control for local LLMs | pip | MIT |
| n8n | Workflow automation platform with AI integration | Docker, npm | Custom |
| n8n Ollama Desktop | Desktop app combining n8n and Ollama with a model-management UI | Download | Apache-2.0 |
| ollama-loop-guard | Proxy that detects runaway thinking loops and interrupts with in-stream regeneration | pip | MIT |
| Reply Better AI | Browser extension to improve writing and draft replies on any page, on-device or via a local server | Browser extension | MIT |
| VoxFlow | Offline voice dictation: hold a hotkey, speak, a local model writes it at your cursor | Download | MIT |
| Name/Link | Description | Install | License |
|---|---|---|---|
| bean | Picks the right local model for your hardware, downloads it, and hands off to the app | Download | MIT |
| lucinate | Multi-backend terminal AI chat client for OpenAI-compatible APIs | Download | Apache-2.0 |
| modelfit | Detects your hardware and recommends the best local model that fits, with JSON output | npm | MIT |
| Nanocoder | Local-first terminal coding agent, bring your own model | npm | MIT |
| ollama-top | htop-style terminal UI for local models, GPUs and batch pipelines | Download | MIT |
| osync | Copy local Ollama models to any accessible remote Ollama instance, C# .NET 8, Windows, macOS, Linux x64/arm64 | Download | MIT |
| otaku | LLM frontend for roleplay | pip | AGPL-3.0 |
| quickthink | Local-first CLI and library wrapping LLM calls with plan-then-answer compression and latency-aware routing | pip | Apache-2.0 |
| Quorum | Multi-agent AI discussions with Ollama auto-discovery and 7 debate methods | pip | Custom |
| Samuraizer | Local-first meeting transcription, summaries, action items and decisions via Whisper | npm | MIT |
| Sifty | Windows maintenance CLI/TUI with an optional local assistant explaining what is safe to clean | pip | MIT |
| Name/Link | Description | Install | License |
|---|---|---|---|
| LLM Colosseum | Real-time RTS arena evaluating LLM tool calling, format discipline and latency | Source | MIT |
| LLMxRay | Local observability UI: token streaming, prompt-cache measurement, logprob benchmarks | npm, Docker | Apache-2.0 |
| Local LLM Arena | Side-by-side local model comparison with blind voting, LLM-as-judge and a private Elo leaderboard | Docker | MIT |
| mac-llm-calculator | Works out whether a model fits a Mac unified memory and expected tokens per second | pip | MIT |
| Ollama Grid Search | Desktop app to evaluate and compare LLM models | Download | MIT |
| OMeter | Benchmark and compare Ollama models across local and cloud endpoints | pip | MIT |
| Remuda | Test and tune local models with a built-in Modelfile editor | Homebrew | MIT |
| Name/Link | Description | Install | License |
|---|---|---|---|
| LangChain.dart Ollama | Ollama integration for LangChain.dart | pub | MIT |
| marimo | Interactive computing environment with Ollama support | pip | Apache-2.0 |
| Ollama SDK for .NET | Based on OpenAPI specification, From .Net Framework to .NET 8 including latest features like trimming | NuGet | MIT |
| Ollama SDK for Dart | Dart client for Ollama API | pub | MIT |
| PraisonAI | Multi-agent framework with Ollama support | pip, npm | MIT |