{"id":100769,"url":"https://github.com/ethicals7s/awesome-local-ai","name":"awesome-local-ai","description":"152 open-source tools to run LLMs 100% locally – no cloud, no API keys, no censorship","projects_count":133,"last_synced_at":"2026-10-24T10:00:21.818Z","repository":{"id":327733619,"uuid":"1107063338","full_name":"ethicals7s/awesome-local-ai","owner":"ethicals7s","description":"152 open-source tools to run LLMs 100% locally – no cloud, no API keys, no censorship","archived":false,"fork":false,"pushed_at":"2025-11-30T14:08:32.000Z","size":9,"stargazers_count":114,"open_issues_count":18,"forks_count":18,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-10-05T03:57:38.554Z","etag":null,"topics":["awesome-list","crewai","exllama","fine-tuning","inference","llama-cpp","local-ai","local-llm","machine-learning-ai","multi-modal","offline-ai","ollama","private-gpt","quantization","rag-agents","self-hosted","vllm","voice"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc0-1.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ethicals7s.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-11-30T14:07:16.000Z","updated_at":"2026-10-04T17:08:32.000Z","dependencies_parsed_at":null,"dependency_job_id":"6e4038b5-2d50-4fa8-b8cc-519bd63df3b7","html_url":"https://github.com/ethicals7s/awesome-local-ai","commit_stats":null,"previous_names":["ethicals7s/awesome-local-ai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ethicals7s/awesome-local-ai","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethicals7s%2Fawesome-local-ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethicals7s%2Fawesome-local-ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethicals7s%2Fawesome-local-ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethicals7s%2Fawesome-local-ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ethicals7s","download_url":"https://codeload.github.com/ethicals7s/awesome-local-ai/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethicals7s%2Fawesome-local-ai/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":345237552,"owners_count":38482437,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-10-03T21:59:58.778Z","status":"online","status_checked_at":"2026-10-24T02:00:07.043Z","response_time":103,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2025-12-24T21:17:12.267Z","updated_at":"2026-10-24T10:00:21.819Z","primary_language":"Python","list_of_lists":false,"displayable":true,"categories":["Fine-tuning \u0026 Quantization (18)","Voice \u0026 Multimodal (local) (16)","Desktop \u0026 Web UIs (22)","Inference Engines \u0026 Backends (22)","One-Click Runners \u0026 Installers (15)","RAG \u0026 Vector Databases (14)","Agent Frameworks (fully local) (25)","Contribute"],"sub_categories":[],"readme":"# Awesome Local AI\n\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n[![Star History](https://api.star-history.com/svg?repos=ethicals7s/awesome-local-ai\u0026type=Date)](https://star-history.com/#ethicals7s/awesome-local-ai\u0026Date)\n\n\u003e Curated list of the best **open-source** tools to run, fine-tune, and build with LLMs **100% locally** in 2025–2026  \n\u003e No cloud · No API keys · No censorship — **152 tools with descriptions and growing**\n\n**Star this repo to keep the ultimate local-AI toolbox at hand → updated weekly**\n\n## One-Click Runners \u0026 Installers (15)\n- [Ollama](https://ollama.com) – One-command runner for Llama 3, Gemma, Mistral, etc.\n- [LM Studio](https://lmstudio.ai) – Beautiful GUI for discovering and chatting with local models\n- [GPT4All](https://gpt4all.io) – Fully offline chat with 100+ quantized models\n- [Jan](https://jan.ai) – Open-source ChatGPT alternative that runs locally\n- [Llama.cpp](https://github.com/ggerganov/llama.cpp) – High-performance C++ inference engine (GGUF)\n- [text-generation-webui](https://github.com/oobabooga/text-generation-webui) – Feature-rich web UI with LoRAs and extensions\n- [AnythingLLM](https://anythingllm.com) – Local RAG + document chat workspace\n- [PrivateGPT](https://github.com/imartinez/privateGPT) – Offline Q\u0026A over your documents\n- [KoboldCpp](https://github.com/LostRuins/koboldcpp) – Single-file GGUF runner with KoboldAI API\n- [Pinokio](https://pinokio.computer) – One-click browser installer for AI apps\n- [LocalAI](https://localai.io) – OpenAI API drop-in replacement for local models\n- [Faraday.dev](https://faraday.dev) – Desktop character chat with local models\n- [Tabby](https://github.com/TabbyML/tabby) – Self-hosted GitHub Copilot alternative\n- [Cortex](https://github.com/janhq/cortex.cpp) – Embeddable multi-engine runner\n- [LMDeploy](https://github.com/InternLM/lmdeploy) – Model compression and deployment toolkit\n\n## Desktop \u0026 Web UIs (22)\n- [Open WebUI](https://openwebui.com) – Official gorgeous frontend for Ollama\n- [LobeChat](https://lobechat.com) – Modern multi-model chat UI with local backends\n- [Chainlit](https://chainlit.io) – Build conversational AI apps fast\n- [Gradio](https://gradio.app) – Instant web demos for any model\n- [LoLLMS WebUI](https://github.com/ParisNeo/lollms) – All-in-one local LLM interface\n- [SillyTavern](https://github.com/SillyTavern/SillyTavern) – Advanced roleplay chat UI\n- [LibreChat](https://librechat.ai) – Multi-provider chat with local support\n- [Continue.dev](https://continue.dev) – Local VSCode Copilot\n- [Aider](https://aider.chat) – Terminal pair programmer with git integration\n- [Open Interpreter](https://openinterpreter.com) – Run code and control your computer locally\n- [ComfyUI](https://github.com/comfyanonymous/ComfyUI) – Node-based Stable Diffusion workflow\n- [InvokeAI](https://invoke.ai) – Creative image generation UI\n- [Fooocus](https://github.com/lllyasviel/Fooocus) – Simplified high-quality image generation\n- [Draw Things](https://drawthings.ai) – macOS/iOS Stable Diffusion app\n- [Msty](https://msty.app) – Minimalist local chat app\n- [LlamaGPT](https://github.com/getumbrel/llama-gpt) – Self-hosted chat on Umbrel\n- [Text Generation UI](https://github.com/oobabooga/text-generation-webui) – Versatile text gen web UI\n- [Chatbot UI](https://github.com/mckaywrigley/chatbot-ui) – Clean self-hosted ChatGPT-like interface\n- [HuggingChat](https://huggingface.co/chat) – Self-hosted version of HF chat\n- [Taskyon](https://github.com/Xyntopia/taskyon) – Vue3-based local-first chat UI\n- [QA-Pilot](https://github.com/reid41/QA-Pilot) – Interactive repo/file chat\n- [Shell-Pilot](https://github.com/reid41/shell-pilot) – LLM-powered shell scripting\n\n## Agent Frameworks (fully local) (25)\n- [CrewAI](https://crewai.com) – Multi-agent orchestration framework\n- [AutoGen](https://microsoft.github.io/autogen/) – Microsoft conversational multi-agent system\n- [LangGraph](https://github.com/langchain-ai/langgraph) – Stateful multi-actor applications\n- [BabyAGI](https://github.com/yoheinakajima/babyagi) – Task-driven autonomous agent\n- [Auto-GPT](https://github.com/Significant-Gravitas/Auto-GPT) – Experimental autonomous GPT agent\n- [GPT Engineer](https://github.com/AntonOsika/gpt-engineer) – Generate codebases from specifications\n- [MetaGPT](https://github.com/geekan/MetaGPT) – Multi-agent software company simulation\n- [SuperAGI](https://github.com/TransformerOptimus/SuperAGI) – Infrastructure for autonomous agents\n- [Devon](https://github.com/entropy-research/Devon) – Open-source AI software engineer\n- [Open Interpreter](https://github.com/KillianLucas/open-interpreter) – Natural language code execution\n- [Aider](https://github.com/paul-gauthier/aider) – Git-aware pair programmer\n- [Langflow](https://github.com/langflow-ai/langflow) – Visual LLM app builder\n- [Flowise](https://flowiseai.com) – Drag-and-drop LLM flows (self-hosted)\n- [Dify](https://dify.ai) – Open-source LLM app builder (self-hosted)\n- [Haystack](https://haystack.deepset.ai) – End-to-end NLP pipelines\n- [LlamaIndex](https://www.llamaindex.ai) – Data framework for LLM applications\n- [Bisheng](https://github.com/dataelement/bisheng) – Low-code agent builder\n- [Taskweaver](https://github.com/microsoft/TaskWeaver) – Code-first agent framework\n- [XAgent](https://github.com/OpenBMB/XAgent) – Autonomous agent with tools\n- [ChatDev](https://github.com/OpenBMB/ChatDev) – Collaborative software development agents\n- [GodMode](https://github.com/smol-ai/godmode) – Prompt chaining for complex tasks\n- [SmolAgents](https://github.com/smol-ai/agents) – Lightweight agent framework\n- [Camel-AI](https://github.com/camel-ai/camel) – Communicative agents for role-playing\n- [AgentGPT](https://github.com/reworkd/AgentGPT) – Browser-based autonomous agents (local mode)\n- [PrivateGPT](https://github.com/imartinez/privateGPT) – Local agent for document querying\n\n## RAG \u0026 Vector Databases (14)\n- [Chroma](https://www.trychroma.com) – Lightweight embedded vector database\n- [Weaviate](https://weaviate.io) – Open-source vector search engine\n- [Qdrant](https://qdrant.tech) – High-performance filtered vector search\n- [LanceDB](https://lancedb.com) – Serverless vector DB on Parquet\n- [Milvus](https://milvus.io) – Scalable open-source vector database\n- [Faiss](https://github.com/facebookresearch/faiss) – Facebook similarity search library\n- [Pinecone](https://pinecone.io) – Self-hosted vector database\n- [Vespa](https://vespa.ai) – Big data serving with vector search\n- [Typesense](https://typesense.org) – Typo-tolerant search with vectors\n- [Redis Vector Library](https://redis.io) – In-memory vector similarity\n- [PGVector](https://github.com/pgvector/pgvector) – Postgres vector extension\n- [DuckDB](https://duckdb.org) – In-process OLAP with vector support\n- [SurrealDB](https://surrealdb.com) – Multi-model DB with vector indexing\n- [Zilliz](https://zilliz.com) – Cloud-native vector platform (open components)\n\n## Fine-tuning \u0026 Quantization (18)\n- [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) – YAML-driven LoRA/QLoRA fine-tuning\n- [Unsloth](https://github.com/unslothai/unsloth) – 2× faster fine-tuning on consumer GPUs\n- [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) – Web UI for efficient fine-tuning\n- [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) – GPTQ/AWQ quantization toolkit\n- [PEFT](https://github.com/huggingface/peft) – Parameter-efficient fine-tuning methods\n- [TRL](https://github.com/huggingface/trl) – RLHF, DPO, PPO training\n- [Lit-GPT](https://github.com/Lightning-AI/lit-gpt) – Lightweight fine-tuning with PyTorch Lightning\n- [OpenRLHF](https://github.com/OpenRLHF/OpenRLHF) – Scalable RLHF framework\n- [DeepSpeed](https://github.com/microsoft/DeepSpeed) – Deep learning optimization library\n- [Colossal-AI](https://github.com/hpcaitech/ColossalAI) – Large model training system\n- [Megatron-LM](https://github.com/NVIDIA/Megatron-LM) – Efficient transformer training\n- [BMTrain](https://github.com/OpenBMB/BMTrain) – Communication-efficient training\n- [FSDP](https://pytorch.org/docs/stable/fsdp.html) – Fully Sharded Data Parallel\n- [LoRAX](https://github.com/predibase/lorax) – Multi-LoRA serving\n- [BitsAndBytes](https://github.com/TimDettmers/bitsandbytes) – 8-bit optimizers and quantization\n- [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa) – 4-bit LLaMA quantization\n- [ExLlama](https://github.com/turboderp/exllama) – Fast LLaMA inference with quantization\n- [ExLlamaV2](https://github.com/turboderp/exllamav2) – Optimized quantized inference\n\n## Voice \u0026 Multimodal (local) (16)\n- [Whisper.cpp](https://github.com/ggerganov/whisper.cpp) – Fast local speech-to-text\n- [Coqui TTS](https://github.com/coqui-ai/TTS) – Neural text-to-speech synthesis\n- [OpenVoice](https://github.com/myshell-ai/OpenVoice) – Instant voice cloning\n- [Silero Models](https://github.com/snakers4/silero-models) – Pre-trained TTS/STT models\n- [LLaVA](https://llava-vl.github.io) – Vision + text multimodal chat\n- [Moondream2](https://github.com/vikhyat/moondream) – Compact vision-language model\n- [Bark](https://github.com/suno-ai/bark) – Text-to-audio with voice cloning\n- [Audiocraft](https://github.com/facebookresearch/audiocraft) – Music and audio generation\n- [RVC WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) – Voice conversion\n- [Tortoise TTS](https://github.com/neonbjb/tortoise-tts) – High-quality multi-voice TTS\n- [VALL-E X](https://github.com/Plachtaa/VALL-E-X) – Zero-shot TTS from short audio\n- [Piper TTS](https://github.com/rhasspy/piper) – Fast neural TTS\n- [OpenTTS](https://github.com/synesthesiam/opentts) – Multi-speaker TTS\n- [Kosmos-2](https://github.com/microsoft/unilm/tree/master/kosmos-2) – Grounded image-text model\n- [ImageBind](https://github.com/facebookresearch/ImageBind) – Multimodal embedding across 6 modalities\n- [CLIP](https://github.com/openai/CLIP) – Contrastive language-image pretraining\n\n## Inference Engines \u0026 Backends (22)\n- [vLLM](https://github.com/vllm-project/vllm) – High-throughput serving with PagedAttention\n- [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) – NVIDIA-optimized low-latency inference\n- [ExLlamaV2](https://github.com/turboderp/exllamav2) – Blazing-fast quantized inference\n- [SGLang](https://github.com/sgl-project/sglang) – Structured generation language\n- [MLX](https://github.com/ml-explore/mlx) – Apple Silicon-native framework\n- [MLC LLM](https://github.com/mlc-ai/mlc-llm) – Universal deployment engine\n- [llama.cpp](https://github.com/ggerganov/llama.cpp) – Lightweight C++ inference\n- [ONNX Runtime](https://onnxruntime.ai) – Cross-platform ML accelerator\n- [OpenVINO](https://github.com/openvinotoolkit/openvino) – Intel-optimized inference\n- [TVM](https://tvm.apache.org) – End-to-end optimizing compiler\n- [GGML](https://github.com/ggerganov/ggml) – Tensor library for ML\n- [CTranslate2](https://github.com/OpenNMT/CTranslate2) – Fast inference engine\n- [FasterTransformer](https://github.com/NVIDIA/FasterTransformer) – NVIDIA transformer decoder\n- [TurboTransformers](https://github.com/Tencent/TurboTransformers) – Kernel fusion inference\n- [LightLLM](https://github.com/ModelTC/lightllm) – Unified inference framework\n- [DeepSpeed-Inference](https://github.com/microsoft/DeepSpeed) – Optimized transformer kernels\n- [FlexFlow](https://github.com/flexflow/FlexFlow) – Distributed deep learning\n- [Ray Serve](https://docs.ray.io/en/latest/serve) – Scalable model serving\n- [BentoML](https://bentoml.com) – ML model serving framework\n- [Triton Inference Server](https://github.com/triton-inference-server/server) – Multi-framework serving\n- [OpenPPL](https://github.com/openppl-public/ppl.nn) – Neural network inference engine\n- [llama.rs](https://github.com/rustformers/llama-rs) – Rust bindings for llama.cpp\n\n## Contribute\nFound something missing? → Open a PR! Let’s get to 200+ together\n\nLast updated: December 1, 2025  \nMade with ❤️ by [@ethicals7s](https://github.com/ethicals7s)\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/ethicals7s%2Fawesome-local-ai/projects"}