Local AI: open-source projects on GitHub
82 repositories on Local AI, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
MEETILY: AI ASSISTANT FOR MEETINGS
Meetily — a local AI assistant for meetings: transcription 4× faster, speaker diarization and summarization via Ollama, all built in Rust.
★ 12,509 · RustSoup: Train LLM Easily
Soup fine-tunes an LLM from a single YAML using a streaming layer — enabling an 8B model to run on a laptop with 4 GB VRAM.
★ 10,552 · PythonODS - YOUR AI SERVER
ODS turns any computer into a powerful AI server: LLM inference, chat, voice, agents, RAG, and image generation.
★ 7,832 · ShellTURBO-FIELDFARE - GEMMA 4 ON MACBOOK
Run Gemma 4 26B‑A4B on any MacBook with an M‑series chip using under 2 GB of RAM. Fast and with no extra resources.
★ 7,391 · SwiftMLX-Powered Laya Decisions
A native MLX runtime for Laya typed decision models that runs short decisions in 7–14 ms on an M3 Max. It avoids text generation, PyTorch, and cloud APIs.
★ 7,102 · PythonRUN VLM LOCALLY ON MAC
mlx-vlm runs and fine-tunes vision-language models (LLaVA, Florence-2, Idefics) on Apple Silicon via MLX. Everything works locally on your Mac without GPU servers.
★ 5,847 · PythonMLX-VLM: RUN VLM ON MAC
Package for running and fine‑tuning Vision Language Models on Mac via MLX. 4.7K★
★ 4,787 · PythonOLARES — YOUR OWN DATA CLOUD
Olares — an open personal cloud platform written in Go for complete control over your data.
★ 4,558 · GoOGAM Offline AI Swiss Knife
OGAM — chat, vision, speech, and image generation offline on your device without keys or network data.
★ 3,380 · TypeScriptFLYENV: LOCAL DEVELOPMENT WITHOUT DOCKER
All-in‑One native environment for Windows/macOS/Linux: an alternative to Docker and XAMPP with PHP, Node.js, Python, databases, and cron jobs.
★ 3,366 · TypeScriptMTPLX SUPERFAST LAUNCH
MTPLX lets you run Qwen 3.8 Flash Next and Qwen 3.8 27B on Mac at 125 tokens/sec in OpenCode. Thanks to MTP speculative decoding on Apple Silicon, results stay accurate a
★ 2,706 · PythonLocal Claude Code
Run Claude Code entirely on-device with Apple Silicon using an MLX-native server compatible with the Anthropic API. Supports local Qwen 3.5 122B, Llama 3.3 70B, and Gemma
★ 2,578 · PythonYOVOICE LOCAL AI STUDIO
Open‑source local AI audio and music studio for macOS and Windows. Clone voices, create songs with lyrics and multi‑track scores — fully offline, zero API fees.
★ 2,193 · TypeScriptLucebox Hub
High-speed server for running LLM locally on consumer hardware. Written in C++ for maximum performance.
★ 2,167 · C++RUN NEURAL NETWORKS LOCALLY
A collection of the best platforms and tools for running LLM on your own hardware. 2000+ stars!
★ 2,045LOCAL OPEN-SOURCE AI AGENT
Atomic-Chat is a private AI engine for running LLM locally without internet, fully offline on your computer. ⭐ 967 stars on GitHub.
★ 2,008 · TypeScriptHOPE-AGENT: SMART AI AGENT FOR DESKTOP
Hope-agent — a cross-platform AI agent in Rust with long-term memory, autonomous goal execution, and dynamic agent orchestration. Supports headless launch on NAS or in th
★ 1,857 · RustLOCAL AI FOR MAC OFFLINE
Nativ runs open LLMs locally on Apple Silicon. No data ever leaves your Mac. Built on MLX and Swift.
★ 1,591 · SwiftMELDWORK: PLATFORM FOR AGENTS
Meldwork — local-first AI‑agent workspace for multi‑agent collaboration. It provides orchestration, scoped permissions, evidence‑aware runs and human‑in‑the‑loop decision
★ 1,578 · JavaScriptVOICE ASSISTANT FOR MAC
Wally lets you control Mac by voice and search local documents offline without internet. It runs on Apple Silicon M1 using an on-device offline LLM via llama.cpp and RAG
★ 1,571 · C++RCLI — Voice AI
Voice AI with RAG, no cloud: chat with Mac and request documents locally.
★ 1,507 · C++PRIVATE AI MEETING NOTES
yogurt — private meeting notes powered by local AI. Works offline via llama.cpp, data never leaves your device.
★ 1,451 · TypeScriptAI Dictation Without Keyboard
Open AI assistant for dictation, working locally and offline. Type three times faster without a keyboard.
★ 1,307 · TypeScriptPHONECLAW: On-device AI Agent
On-device AI agent for smartphones, powered by Gemma 4, provides fast access to intelligent features without the cloud.
★ 1,291 · SwiftHOLLAMA: CHAT WITH LLM IN BROWSER
hollama — a minimal LLM chat that runs entirely in the browser. It connects to local models via Ollama and stores conversations in local storage.
★ 1,199 · TypeScriptOpen AI Workstation
Open‑WebUI Tools — a set of 15+ tools and filters that turn Open WebUI into a powerful AI workstation.
★ 837 · PythonLEXORA AI AGENT
Lexora — an autonomous desktop AI‑agent written in TypeScript, self‑learning and performing real‑world tasks on Arch Linux. It acts as an independent assistant, so capabl
★ 740 · TypeScriptDOC7: Markdown Conversion
Convert any documents into clean Markdown, preserving structure and visual elements, ready for AI models.
★ 718 · GoAI assistant for documents
Secure offline AI assistant for working with thousands of documents without data leakage.
★ 694 · TypeScriptPRIVATE CHAT AI
Local AI chat in the browser using WebGPU and WebLLM, with no servers or cloud data.
★ 642 · TypeScriptwatch-skill - Agent Video Search
Convert agent videos, streams, and screen recordings into a timestamped search index, then verify and fix work via THE LOOP.
★ 582 · PythonJarvis Voice Assistant
Local French voice assistant that works with Claude or Ollama models without an internet connection. It controls Hue lighting, OBS, calendar, and browser, makes Twilio ca
★ 557 · PythonAMADEUS: AI AGENT FOR DESKTOP
Amadeus is a real‑time multimedia desktop agent built on Python, using CUDA, Electron and GPT‑SoVITS. The project is evolving toward a persistent AI OS interface and alre
★ 554 · PythonDEEP SEEKER ON ANDROID
Launch the DeepSeek Harness AI agent on Android without root or Termux — all in one APK with an extension center. Supports local agent execution and API interaction.
★ 535 · KotlinLOCAL AI WITHOUT CLOUD
Hob — open-source desktop client running Gemma and gpt-oss locally on Mac, Windows, and Linux. Works fully offline, no data leaves your machine. Free alternative to Claud
★ 535 · TypeScriptDreamServer: Local AI
DreamServer is an open-source project for running LLMs locally with a chat interface, voice control, agents, workflows, RAG, and image generation, operating without cloud
★ 523 · PythonLOCAL AI UNCENSORED
Desktop app with chat, agent, image and video generation. One .exe, no Docker. 518 ⭐
★ 518 · TypeScriptGERBIL: Local LLMs on Your PC
Desktop app for running large language models right on your computer. No cloud, no subscriptions — full control over AI.
★ 482 · TypeScriptLOCAL AI PHOTO EDITOR ON YOUR GPU
kokon — open-source photo editor by text description. Runs on your GPU: photos never leave computer, no daily limits. One installer for Windows, Mac, Linux sets up Qwen-I
★ 410 · RustZERAIX: LOCAL AI DESKTOP
Local open-source environment for running AI models on device. Speeds up inference without cloud.
★ 405 · TypeScriptCOTABBY AI AutoComplete Mac
Local AI autocomplete for your entire Mac — works offline everywhere you type, with open-source Swift code.
★ 395 · SwiftLOCAL MCP CONTROL PLANE FOR WEB AI
Local MCP controller connecting web assistants to files, terminal, and Git. Executes tools on user machine with permission control.
★ 395 · TypeScriptARENO: Accelerate RL Single Node
ARENO simplifies scaling post-training RL on a single node, delivering high speed with minimal setup.
★ 389 · PythonSTRIX HALO LLM Setup
Guide for LLM on Ryzen AI MAX+ 395 and Radeon 8060S via Ollama, llama.cpp and ROCm. Achieving 100 tokens/s 30B Qwen and 140 tokens/s CHADROCK MTP.
★ 373 · PythonDEEPSEEK API WITHOUT KEYS OR BILLING
Reverse engineered Deepseek chat into OpenAI-compatible API. Access V4 and R1 models via REST without API keys or billing. 326 stars on GitHub.
★ 362 · PythonDEVO — Agent for Any Models
Open-source runtime agent in Rust for private and corporate environments. Supports DeepSeek, Qwen, Kimi, MCP and local code search.
★ 347 · RustLATE-CLI: AI COMMAND IN TERMINAL
Run an AI development command on 5 GB VRAM: ephemeral sub‑agents, precise diffs, a single binary, any model, no config.
★ 342 · GoGUUARDVARK LOCAL AI WORKSTATION
guaardvark — a self‑hosted AI workstation that runs entirely on your hardware. It includes autonomous screen agents, three‑tier neural routing, parallel agent swarms, vid
★ 320 · PythonOFFLINE AI VOICE STUDIO IN RUST
Local app for speech synthesis and recognition with voice cloning and speaker diarization. Works offline, downloads models automatically, supports MCP for AI agents.
★ 312 · RustKNOWLEDGE‑RAG — Local RAG
Local MCP RAG server for Claude Code: hybrid search, cross-encoder, 13 tools and 20 parsers without external servers or API keys.
★ 306 · PythonLLAMASTASH TERMINAL LLM MANAGER
llamastash — terminal-native manager for local LLMs with zero overhead. Launches, supervises, and routes GGUF models via a single OpenAI‑compatible endpoint.
★ 299 · RustGPU BY TURN WITHOUT CRASHES
Berth leases the GPU to chat, image, and voice engines in turn. Two processes never load together and crash each other. Single Go binary, no dependencies.
★ 297 · GoOFFLINE LLM ON ANDROID: FULL PRIVACY
OfflineLLM runs any GGUF models locally via llama.cpp with ARM optimisation. Zero network permissions: encrypted settings, biometric lock, and tamper detection. Supports
★ 291 · KotlinBUILD YOUR AI INTRANET
Autonomous grid unites your computers into a single infrastructure for running AI models: training, fine‑tuning and inference. Supports distributed computing, fine‑tuning
★ 278 · PythonTOSHLLM: RUN LLM ON MAC
TOSHLLM — a native macOS app in Swift that runs large language models locally on Intel‑Mac with AMD GPU, using Metal acceleration. Supports llama.cpp and is compatible wi
★ 258 · SwiftModel-Agnostic Quantization Framework
Quantize and run text, image, video, and audio models across GGUF, llama.cpp, vLLM, Diffusers, and PyTorch with state-of-the-art model-agnostic quantization.
★ 254 · C++PORTABLE HERMES AGENT FOR WINDOWS
Portable Hermes Agent is a desktop for Windows with over 100 AI‑tools, GUI and support for local models via LM Studio. It includes TTS, music generation, ComfyUI workflow
★ 247 · PythonQVAC Local AI SDK
QVAC lets you run LLM, speech recognition, and translation locally on all platforms — from PC to smartphone.
★ 240 · TypeScriptZOTSEEK AI SEARCH IN ZOTERO
ZotSeek adds semantic search to your Zotero library using vector embeddings. The built-in MCP server lets you connect Claude Code and Codex as AI agents for meaning‑based
★ 239 · TypeScriptHOMELAB MONITOR DASHBOARD
Plug‑and‑play dashboard for homelab in a single container: monitoring GPU, local‑AI VRAM, Docker, systemd and host health. Built‑in read‑only MCP server gives AI agents a
★ 236 · PythonNew projects on this topic in Telegram
Telegram →