Local AI Tools
150 tools indexed
Platform
Pricing
| Name | Category | Platform | Pricing | Stars | Compatible |
|---|---|---|---|---|---|
| Hermes Agent Self-improving AI agent with persistent memory, built-in lea | agent-framework | macoslinux | Free | 219.0k | - |
| n8n Self-hosted workflow automation with native LLM, vector DB, | automation | dockerlinux | Free | 197.5k | - |
| Ollama The simplest way to run open-source LLMs locally - pull a | inference-server | macoslinux | Free | 176.7k | - |
| Open WebUI The ChatGPT-style web interface for Ollama and any OpenAI-co | chat-ui | dockerlinux | Free | 146.4k | - |
| ComfyUI Node-based UI for Stable Diffusion, Flux, video generation, | image-gen | windowsmacos | Free | 121.9k | - |
| llama.cpp High-performance LLM inference in pure C/C++ with GPU accele | inference-server | macoslinux | Free | 121.3k | - |
| vLLM High-throughput LLM serving engine with PagedAttention - t | inference-server | linuxdocker | Free | 86.9k | - |
| Odysseus Self-hosted AI workspace with chat, autonomous agents, deep | chat-ui | macoslinux | Free | 83.6k | - |
| AnythingLLM All-in-one local RAG application - workspaces, document ch | rag | dockermacos | Free | 63.7k | - |
| Jan Open-source, offline-first ChatGPT alternative that runs 100 | chat-ui | macoslinux | Free | 43.7k | - |
| Miso One / MisoTTS Open-weight 8B text-to-speech model with human-like emotion, | tts-stt | macoslinux | Free | 3.2k | - |
| AutoGPT Autonomous AI agent that breaks down goals into sub-tasks, e | agent-framework | linuxmacos | Free | 185.6k | - |
| Stable Diffusion WebUI (AUTOMATIC1111) Feature-rich web interface for Stable Diffusion with extensi | image-gen | linuxwindows | Free | 164.2k | - |
| Langflow Low-code visual framework for building multi-agent and RAG a | workflow | webdocker | Free | 152.2k | - |
| Dify Open-source LLM app development platform with visual orchest | workflow | webdocker | Freemium | 149.8k | - |
| LangChain Framework for developing LLM-powered applications with compo | agent-framework | linuxmacos | Free tier | 142.4k | - |
| NextChat Lightweight, cross-platform ChatGPT UI that deploys in one c | chat-ui | webdocker | Free tier | 88.5k | - |
| RAGFlow Open-source RAG engine with deep document understanding for | rag | dockerlinux | Free | 85.7k | - |
| LobeChat Modern, open-source ChatGPT/Claude UI with plugin ecosystem, | chat-ui | webdocker | Free tier | 80.7k | - |
| GPT4All Free-to-use, locally running, privacy-aware chatbot that wor | chat-ui | macoslinux | Free | 77.4k | - |
| LLaMA-Factory Easy-to-use LLM fine-tuning framework with web UI, supportin | fine-tuning | linuxdocker | Free | 73.5k | - |
| Unsloth 2x faster LLM fine-tuning with 50% less memory - supports | fine-tuning | linuxdocker | Free tier | 68.8k | - |
| Open Interpreter Natural language interface that lets LLMs run Python, JavaSc | agent-framework | macoslinux | Free | 67.2k | - |
| Mem0 Intelligent memory layer for AI apps that learns user prefer | other | linuxdocker | Freemium | 61.5k | - |
| CrewAI Framework for orchestrating role-based AI agents that collab | agent-framework | linuxmacos | Free tier | 56.0k | - |
| Flowise Drag-and-drop LLM flow builder with LangChain integration fo | workflow | webdocker | Freemium | 54.8k | - |
| litellm Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs | model-router | - | Free | 54.4k | - |
| Whisper.cpp High-performance, real-time speech-to-text using OpenAI's Wh | tts-stt | macoslinux | Free | 52.2k | - |
| Fooocus Image generation that reimagines Stable Diffusion with a min | image-gen | linuxwindows | Free | 51.2k | - |
| LocalAI Self-hosted, OpenAI-compatible API server for LLMs, image ge | inference-server | linuxdocker | Free | 47.8k | - |
| aider aider is AI pair programming in your terminal | agent-framework | web | Free | 47.6k | - |
| Text Generation WebUI Gradio-based web UI for LLMs supporting multiple inference e | chat-ui | linuxwindows | Free | 47.5k | - |
| textgen Open-source desktop app for local LLMs. Text, vision, tool-c | other | macoslinux | Free | 47.5k | - |
| exo Run frontier AI locally. | other | macos | Free | 46.4k | - |
| TTS 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-te | tts-stt | docker | Free | 45.8k | - |
| Milvus Cloud-native vector database for billion-scale AI similarity | vector-db | dockerlinux | Freemium | 45.3k | - |
| ray Ray is an AI compute engine. Ray consists of a core distribu | inference-server | docker | Free | 43.3k | - |
| Agno Full-stack framework for building multi-modal AI agents with | agent-framework | linuxmacos | Free | 41.4k | - |
| LibreChat Enhanced ChatGPT clone with multi-model, multi-user, and mul | chat-ui | webdocker | Free | 41.1k | - |
| Langchain-Chatchat Langchain-Chatchat(原Langchain-ChatGLM)基于 Langchain 与 ChatGLM | vector-db | docker | Free | 38.5k | - |
| Khoj Open-source, personal AI assistant that searches your notes, | rag | webdocker | Free tier | 35.9k | - |
| Vane Vane is an AI-powered answering engine. | rag | dockerweb | Free | 35.8k | - |
| Continue Open-source AI code assistant that integrates with VS Code a | other | macoslinux | Free tier | 35.0k | - |
| tabby Self-hosted AI coding assistant | agent-framework | dockerweb | Free | 33.8k | - |
| Qdrant High-performance vector search engine written in Rust with r | vector-db | dockerlinux | Freemium | 33.5k | - |
| langfuse 🪢 Open source LLM engineering platform: LLM Observability, | observability | docker | Free | 31.7k | - |
| Onyx Enterprise-grade AI search and chat over your documents, Sla | rag | dockerlinux | Freemium | 31.1k | - |
| SillyTavern Powerful, customizable chat interface for roleplaying with l | chat-ui | webmacos | Free | 31.0k | - |
| cognee Cognee is the open-source AI memory platform for agents. Giv | vector-db | - | Free | 29.2k | - |
| Chroma The AI-native open-source embedding database designed for si | vector-db | dockerlinux | Free tier | 28.9k | - |
| Semantic Kernel Microsoft's SDK for integrating LLMs with C#, Python, and Ja | agent-framework | linuxmacos | Free | 28.3k | - |
| gitleaks Find secrets with Gitleaks 🔑 | fine-tuning | macosdocker | Free | 28.2k | - |
| karakeep A self-hostable bookmark-everything app (links, notes and im | other | macosdocker | Free | 27.7k | - |
| InvokeAI Professional-grade Stable Diffusion toolkit with unified can | image-gen | linuxwindows | Free | 27.6k | - |
| Mastra TypeScript agent framework with built-in model routing, agen | agent-framework | linuxmacos | Free | 26.5k | - |
| meetily Privacy first, AI meeting assistant with 4x faster Parakeet/ | tts-stt | macoswindows | Free | 26.1k | - |
| Haystack Open-source NLP framework for building production-ready RAG | rag | linuxmacos | Free | 26.0k | - |
| Vercel AI SDK Open-source TypeScript toolkit for building AI-powered UIs w | agent-framework | web | Free | 25.7k | - |
| llamafile Distribute and run LLMs with a single file. | tts-stt | macoslinux | Free | 25.4k | - |
| llm-action 本项目旨在分享大模型相关技术原理以及实战经验(大模型工程化、大模型应用落地) | fine-tuning | - | Free | 24.8k | - |
| faster-whisper Faster Whisper transcription with CTranslate2 | tts-stt | - | Free | 24.5k | - |
| Open-Generative-AI Open-source alternative to AI video platforms — Free AI imag | image-gen | macoslinux | Free | 24.4k | - |
| airbyte Open-source data movement for ELT pipelines and AI agents — | agent-framework | - | Free | 21.7k | - |
| omlx LLM inference server with continuous batching & SSD caching | inference-server | macos | Free | 18.1k | - |
| Weaviate Open-source vector database with built-in vectorization, hyb | vector-db | dockerlinux | Freemium | 16.6k | - |
| RagaAI-Catalyst Python SDK for Agent AI Observability, Monitoring and Evalua | observability | - | Free | 16.1k | - |
| self-hosted-ai-starter-kit The Self-hosted AI Starter Kit is an open-source template th | agent-framework | macoslinux | Free | 15.1k | - |
| TensorRT-LLM NVIDIA's optimized LLM inference engine delivering maximum p | inference-server | linux | Free | 14.2k | - |
| Sherpa Onnx Cross-platform speech processing toolkit for STT, TTS, VAD, | tts-stt | linuxwindows | Free | 13.7k | - |
| LitGPT Open-source tool for pretraining, fine-tuning, and deploying | fine-tuning | linuxdocker | Free | 13.5k | - |
| Stable Diffusion Forge Enhanced fork of AUTOMATIC1111's WebUI with 2x faster infere | image-gen | linuxwindows | Free | 12.9k | - |
| OpenLLM Run any open-source LLMs, such as DeepSeek and Llama, as Ope | fine-tuning | docker | Free | 12.4k | - |
| Axolotl Streamlined fine-tuning framework for LLMs with YAML configs | fine-tuning | linuxdocker | Free | 12.2k | - |
| Piper TTS Fast, local neural text-to-speech that runs in real-time on | tts-stt | linuxwindows | Free | 11.3k | - |
| Hugging Face Text Generation Inference Production-ready LLM inference server from Hugging Face with | inference-server | linuxdocker | Free | 10.9k | - |
| blinko An open-source, self-hosted personal AI note tool prioritizi | other | macoslinux | Free | 10.8k | - |
| openvino OpenVINO™ is an open source toolkit for optimizing and deplo | tts-stt | - | Free | 10.6k | - |
| PowerInfer High-speed Large Language Model Serving for Local Deployment | inference-server | windows | Free | 9.7k | - |
| local-deep-research ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all | rag | docker | Free | 8.8k | - |
| BentoML The easiest way to serve AI apps and models - Build Model In | inference-server | dockerweb | Free | 8.7k | - |
| AIClient2API Self-hosted multi-protocol AI API proxy for Antigravity, Cod | model-router | docker | Free | 8.5k | - |
| Kokoro TTS High-quality, lightweight neural TTS with 10+ voices, 2x fas | tts-stt | linuxmacos | Free | 8.1k | - |
| webiny-js Open-source, self-hosted CMS platform on AWS serverless (Lam | other | - | Free | 8.0k | - |
| lmdeploy LMDeploy is a toolkit for compressing, deploying, and servin | inference-server | - | Free | 8.0k | - |
| dynamo A Datacenter Scale Distributed Inference Serving Framework | image-gen | dockerweb | Free | 7.6k | - |
| opencommit top #1 and most feature rich GPT wrapper for git — generate | other | docker | Free | 7.5k | - |
| sandstorm Sandstorm is a self-hostable web productivity suite. It's im | other | linuxweb | Free | 7.1k | - |
| plano Plano is an AI-native proxy and data plane for agentic apps | observability | docker | Free | 6.9k | - |
| openevolve Open-source implementation of AlphaEvolve | agent-framework | macos | Free | 6.8k | - |
| ClawRouter The agent-native LLM router for autonomous agents. 55+ model | model-router | - | Free | 6.7k | - |
| open-multi-agent From a goal to a task DAG, automatically. TypeScript-native | agent-framework | - | Free | 6.6k | - |
| TaxHacker Self-hosted AI accounting app. LLM analyzer for receipts, in | other | - | Free | 6.5k | - |
| intentkit IntentKit is an open-source, self-hosted cloud agent cluster | agent-framework | dockerweb | Free | 6.5k | - |
| agentic-inbox A self-hosted email client with an AI agent, running entirel | agent-framework | web | Free | 6.5k | - |
| Genkit Google's open-source framework for building AI-powered appli | agent-framework | linuxmacos | Free | 6.3k | - |
| FunClip FunASR-powered video transcription, subtitle generation, and | tts-stt | web | Free | 6.0k | - |
| flashinfer FlashInfer: Kernel Library for LLM Serving | inference-server | web | Free | 6.0k | - |
| whichllm Find the local LLM that actually runs and performs best on y | inference-server | - | Free | 6.0k | - |
| mission-control Self-hosted AI agent orchestration platform: dispatch tasks, | agent-framework | docker | Free | 5.8k | - |
| Torchtune PyTorch-native library for easily fine-tuning LLMs with memo | fine-tuning | linuxmacos | Free | 5.8k | - |
| kserve Standardized Distributed Generative and Predictive AI Infere | inference-server | docker | Free | 5.7k | - |
| shimmy ⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, | inference-server | - | Free | 5.7k | - |
| cactus Low-latency AI engine for mobile devices & wearables | tts-stt | macos | Free | 5.5k | - |
| baserow Build databases, automations, apps & agents with AI — no cod | agent-framework | docker | Free | 5.4k | - |
| gpustack A GPU cluster manager that configures and orchestrates infer | inference-server | docker | Free | 5.4k | - |
| superduper Superduper: End-to-end framework for building custom AI appl | vector-db | - | Free | 5.3k | - |
| xtuner A Next-Generation Training Engine Built for Ultra-Large MoE | fine-tuning | - | Free | 5.2k | - |
| lemonade Lemonade helps users discover and run local AI apps by servi | inference-server | macoslinux | Free | 5.0k | - |
| dograh Open source voice AI platform. Self-hosted alternative to Va | tts-stt | docker | Free | 5.0k | - |
| openmed Local-first healthcare AI: clinical NER & HIPAA PII de-ident | other | macos | Free | 4.7k | - |
| ExLlamaV2 Fast inference library for quantized LLMs optimized for sing | inference-server | linuxwindows | Free | 4.6k | - |
| ai-agents-from-scratch Demystify AI agents by building them yourself. Local LLMs, n | agent-framework | - | Free | 4.4k | - |
| SwarmUI Modern, modular Stable Diffusion UI with ComfyUI integration | image-gen | linuxwindows | Free | 4.4k | - |
| OpenMemory Local persistent memory store for LLM applications including | vector-db | web | Free | 4.4k | - |
| langroid Harness LLMs with Multi-Agent Programming | rag | docker | Free | 4.1k | - |
| lorax Multi-LoRA inference server that scales to 1000s of fine-tun | fine-tuning | docker | Free | 3.8k | - |
| LLamaSharp A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local d | chat-ui | - | Free | 3.7k | - |
| farfalle 🔍 AI search engine - self-host with local or cloud LLMs | other | dockerweb | Free | 3.5k | - |
| surf Personal AI Notebooks. Organize files & webpages and generat | rag | macoslinux | Free | 3.5k | - |
| DreamServer Turn your PC, Mac, or Linux box into an AI server. LLM infe | tts-stt | macoslinux | Free | 3.5k | - |
| ODS Turn your PC, Mac, or Linux box into an AI server. LLM infe | tts-stt | macoslinux | Free | 3.5k | - |
| METATRON AI-powered penetration testing assistant using local LLM on | other | linuxweb | Free | 3.3k | - |
| Rapid-MLX The fastest local AI engine for Apple Silicon. 4.2x faster t | inference-server | macos | Free | 3.3k | - |
| Sidekick A native macOS app that allows users to chat with a local LL | rag | macosweb | Free | 3.3k | - |
| nexu The simplest desktop client for OpenClaw 🦞 — bridge your Ag | agent-framework | macoswindows | Free | 3.2k | - |
| algernon Small self-contained pure-Go web server with Lua, Teal, Mark | other | dockerweb | Free | 3.0k | - |
| claude-code-local Run Claude Code 100% on-device with local AI on Apple Silico | tts-stt | macosweb | Free | 3.0k | - |
| llm_aided_ocr Enhances Tesseract OCR output using LLMs (local or API) for | other | - | Free | 2.9k | - |
| DeepCamera Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveil | agent-framework | macosdocker | Free | 2.9k | - |
| lucebox-hub Fast LLM speculative inference server for consumer hardware. | inference-server | - | Free | 2.7k | - |
| lucebox Fast LLM speculative inference server for consumer hardware. | inference-server | - | Free | 2.7k | - |
| TranslateBooksWithLLMs Translate full-length books and documents with Ollama, OpenA | other | macoswindows | Free | 2.2k | - |
| openai-edge-tts Free, high-quality text-to-speech API endpoint to replace Op | tts-stt | docker | Free | 2.0k | - |
| USB-Uncensored-LLM The ultimate zero-install, portable local AI environment. Ru | other | macoslinux | Free | 1.9k | - |
| parlor On-device, real-time multimodal AI. Have natural voice and v | tts-stt | macoslinux | Free | 1.9k | - |
| little-coder A coding agent optimized to smaller LLMs | agent-framework | - | Free | 1.8k | - |
| lmstudio-js LM Studio TypeScript SDK | other | web | Free | 1.7k | - |
| row-bot Row-Bot - Personal AI Sovereignty. A local-first AI assistan | tts-stt | macoslinux | Free | 1.4k | - |
| mlx-tune Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRP | tts-stt | macos | Free | 1.4k | - |
| TabbyAPI Lightweight, OpenAI-compatible API server for ExLlamaV2 with | inference-server | linuxwindows | Free | 1.3k | - |
| PhoneClaw Mobile-native local AI Agent framework for phones and edge d | model-router | macos | Free | 1.2k | - |
| Atomic-Chat Local AI app and inference engine for agents. Run open-weigh | agent-framework | macoslinux | Free | 1.1k | - |
| web-search-mcp A simple, locally hosted Web Search MCP server for use with | other | macoslinux | Free | 1.0k | - |
| SwiftLM ⚡ Native MLX Swift LLM inference server for Apple Silicon. O | inference-server | macos | Free | 0.7k | - |
| candle-vllm Efficent platform for inference and serving local LLMs inclu | inference-server | macosdocker | Free | 0.7k | - |
| Vibe-Workflow Free, open-source alternative to Weavy AI, Krea Nodes, Freep | image-gen | web | Free | 0.5k | - |
| willow-inference-server Open source, local, and self-hosted highly optimized languag | tts-stt | linuxdocker | Free | 0.5k | - |
| mlx-serve Native LLM inference server for Apple Silicon. OpenAI + Anth | tts-stt | macos | Free | 0.4k | - |
| izwi Voice AI runtime. Local first transcription, speaker diariza | tts-stt | macoslinux | Free | 0.4k | - |
| LM Studio Desktop GUI for running local LLMs - model browser, chat, | chat-ui | macoslinux | Free tier | - | - |