Open-source AI software directory
100 open-source AI tools for images, video, audio, LLMs and coding — each with step-by-step install guides, system requirements, live GitHub stats and alternatives.
Categories
Image generationWeb UIs and apps for running Stable Diffusion, FLUX and other open models on your own GPU.19 toolsImage editing & upscalingUpscalers, background removers, inpainting tools and face restoration you can run locally.10 toolsVideo generationText-to-video, image-to-video and talking-head models and apps with open weights.9 toolsAudio & voiceSpeech-to-text, text-to-speech, voice cloning, stem separation and music generation.17 toolsLocal LLM runnersInference engines and desktop apps that run Llama, Qwen, Mistral and other open models on your machine.11 toolsChat UIs, RAG & agentsSelf-hosted ChatGPT-style interfaces, document Q&A and workflow builders for LLM apps.17 toolsAI codingEditor extensions, terminal agents and self-hosted code completion.10 toolsTraining & fine-tuningLoRA trainers for image models and efficient fine-tuning frameworks for LLMs.7 tools
All software
ComfyUINode-based interface for diffusion models — images, video and audio.GPL-3.0Stable Diffusion WebUI (AUTOMATIC1111)The classic browser UI for Stable Diffusion with a massive extension ecosystem.AGPL-3.0Stable Diffusion WebUI ForgeA faster, leaner fork of the A1111 WebUI with FLUX support.AGPL-3.0FooocusMidjourney-like simplicity for SDXL: type a prompt and press Generate.GPL-3.0InvokeAIProfessional creative engine with a unified canvas for Stable Diffusion and FLUX.Apache-2.0SD.NextAll-in-one WebUI supporting dozens of diffusion models and every GPU backend.Apache-2.0SwarmUIA friendly generate tab on top of ComfyUI, with multi-GPU support.MITStability MatrixPackage manager that installs and updates every popular Stable Diffusion UI.AGPL-3.0PinokioA one-click “AI browser” that installs and runs open-source AI apps locally.MITKrita AI DiffusionGenerate and inpaint inside the Krita painting app.GPL-3.0DiffusersHugging Face’s Python library for diffusion models.Apache-2.0ComfyUI-ManagerInstall, update and manage ComfyUI custom nodes and models.GPL-3.0ControlNet for SD WebUIControlNet extension for the A1111 WebUI: pose, depth, edges and more.GPL-3.0IP-AdapterUse an image as a prompt — style and subject transfer for diffusion models.Apache-2.0InstantIDIdentity-preserving generation from a single face photo.Apache-2.0PhotoMakerCustomize realistic photos of a person from a few reference images.Apache-2.0FLUX (reference code)Official inference code for Black Forest Labs’ FLUX models.Apache-2.0Stability AI Generative ModelsStability AI’s reference code for SDXL and Stable Video Diffusion.MITDiffusionBeeThe simplest way to run Stable Diffusion on a Mac.AGPL-3.0UpscaylFree desktop app that upscales images with AI.AGPL-3.0Real-ESRGANPractical image and video super-resolution models.BSD-3-ClauseGFPGANBlind face restoration for old and low-quality photos.Apache-2.0CodeFormerRobust face restoration with an adjustable fidelity–quality trade-off.S-Lab License 1.0 (non-commercial)rembgRemove image backgrounds from the command line, Python or an HTTP server.MITBiRefNetHigh-resolution dichotomous segmentation — state-of-the-art background removal.MITIOPaintErase objects, watermarks and people with AI inpainting (formerly Lama Cleaner).Apache-2.0Segment Anything (SAM)Meta’s promptable segmentation model — click to cut out any object.Apache-2.0SAM 2Segment Anything for images and video, with object tracking.Apache-2.0chaiNNerNode-based image processing GUI for upscaling and batch pipelines.GPL-3.0Wan 2.2Alibaba’s open-weight video generation models (text, image and speech to video).Apache-2.0HunyuanVideoTencent’s 13B-parameter open video foundation model.Tencent Hunyuan Community LicenseCogVideoXOpen text-to-video and image-to-video models from Zhipu AI / Tsinghua.Apache-2.0LTX-VideoFast, real-time-capable open video generation from Lightricks.Apache-2.0FramePackLong image-to-video generation on laptop GPUs with as little as 6 GB VRAM.Apache-2.0AnimateDiffAnimate your Stable Diffusion checkpoints with plug-in motion modules.Apache-2.0LivePortraitAnimate a portrait photo with the expressions of a driving video.MITSadTalkerMake a single photo talk from an audio file.Apache-2.0Open-SoraFully open-source video generation: weights, training code and data pipeline.Apache-2.0WhisperOpenAI’s open-source speech recognition and translation model.MITwhisper.cppWhisper in plain C/C++ — fast on CPUs, Apple Silicon and mobile.MITfaster-whisperWhisper reimplemented on CTranslate2 — up to 4× faster with less memory.MITWhisperXFast transcription with word-level timestamps and speaker diarization.BSD-2-ClauseCoqui TTSDeep-learning text-to-speech toolkit, including the XTTS voice cloning model.MPL-2.0GPT-SoVITSFew-shot voice cloning and TTS with a full training WebUI.MITRVC WebUIRetrieval-based voice conversion — train a voice model and convert singing or speech.MITApplioA modern, easier RVC-based voice conversion app.MITF5-TTSZero-shot voice cloning TTS based on flow matching.MITFish SpeechMultilingual TTS and voice cloning from Fish Audio.Apache-2.0KokoroA tiny 82M-parameter TTS model with surprisingly natural voices.Apache-2.0ChatTTSConversational TTS for dialogue, with laughter and pauses.AGPL-3.0BarkSuno’s generative audio model: speech, music snippets and sound effects.MITAudioCraft (MusicGen)Meta’s library for MusicGen music generation and AudioGen sound effects.MITStable Audio ToolsTraining and inference code for Stable Audio Open.MITDemucsSeparate vocals, drums, bass and other stems from any song.MITUltimate Vocal RemoverDesktop GUI for vocal removal and stem separation.MITOllamaGet up and running with large language models locally.MITllama.cppLLM inference in C/C++ — the engine behind most local AI apps.MITJanOpen-source ChatGPT-style desktop app that runs 100% offline.AGPL-3.0GPT4AllPrivate, on-device chat with local document Q&A.MITLocalAISelf-hosted, OpenAI-compatible API for text, images, audio and more.MITvLLMHigh-throughput LLM serving engine with PagedAttention.Apache-2.0SGLangFast serving framework for LLMs and vision-language models.Apache-2.0Text Generation WebUIThe “AUTOMATIC1111 of text generation” — a Gradio UI for local LLMs.AGPL-3.0KoboldCppSingle-file llama.cpp-based runner for GGUF models with a story-writing UI.AGPL-3.0llamafileDistribute and run an LLM as a single executable file.Apache-2.0MLX LMRun and fine-tune LLMs on Apple Silicon with Apple’s MLX framework.MITOpen WebUISelf-hosted ChatGPT-style interface for Ollama and OpenAI-compatible APIs.Open WebUI License (BSD-3-Clause based)LibreChatOpen-source ChatGPT clone supporting every major AI provider.MITLobeChatModern AI chat framework with plugins, knowledge base and agent market.LobeHub Community LicenseNextChatLightweight cross-platform ChatGPT/Gemini/Claude chat client.MITChatboxDesktop client for ChatGPT, Claude, Gemini and local models.GPL-3.0AnythingLLMAll-in-one desktop and Docker app for private document chat and agents.MITDifyVisual platform for building LLM apps, RAG pipelines and agents.Dify Open Source License (Apache-2.0 based)FlowiseDrag-and-drop UI to build LLM flows and agents.Apache-2.0LangflowVisual builder for AI agents and RAG apps, deployable as APIs or MCP servers.MITn8nWorkflow automation with native AI agents and 400+ integrations.Sustainable Use License (fair-code)RAGFlowRAG engine built on deep document understanding.Apache-2.0SillyTavernPower-user chat frontend for characters, roleplay and storytelling.AGPL-3.0CrewAIPython framework for orchestrating role-playing, collaborative AI agents.MITAutoGenMicrosoft’s framework for building multi-agent AI applications.MITLangChainThe most widely used framework for building LLM applications.MITLlamaIndexData framework for connecting LLMs to your documents.MITBrowser UseLet AI agents control a real web browser.MITContinueOpen-source AI code assistant for VS Code and JetBrains.Apache-2.0ClineAutonomous coding agent inside VS Code that asks before it acts.Apache-2.0Roo CodeA team of AI coding agents in your editor, with custom modes.Apache-2.0AiderAI pair programming in your terminal, with automatic git commits.Apache-2.0opencodeOpen-source AI coding agent built for the terminal.MITCodex CLIOpenAI’s lightweight coding agent for your terminal.Apache-2.0Gemini CLIGoogle’s open-source AI agent for the terminal.Apache-2.0TabbySelf-hosted AI coding assistant — an open-source Copilot alternative.Apache-2.0OpenHandsOpen platform for autonomous software development agents.MITOpen InterpreterA natural-language interface that runs code on your computer.AGPL-3.0Kohya’s GUIGUI for training LoRA, DreamBooth and fine-tunes for SD, SDXL and FLUX.Apache-2.0OneTrainerOne-stop trainer for diffusion models with a desktop UI.AGPL-3.0AI ToolkitOstris’ training suite for FLUX, video and image model LoRAs.MITUnslothFine-tune LLMs 2× faster with up to 70% less memory.Apache-2.0AxolotlConfig-driven LLM fine-tuning for many models and techniques.Apache-2.0LLaMA-FactoryUnified fine-tuning for 100+ LLMs and VLMs with a no-code web UI.Apache-2.0TRLHugging Face’s library for post-training LLMs: SFT, DPO, GRPO.Apache-2.0