Local AI Workstations RAG Tools
Complete desktop/web GUI applications that bundle multiple AI capabilities (chat, RAG, image generation, voice, model management) into single integrated platforms for local/offline use. Does NOT include single-purpose tools, cloud-dependent services, or component libraries without a full user interface.
There are 87 local ai workstations tools tracked. 2 score above 70 (verified tier). The highest-rated is langbot-app/LangBot at 87/100 with 15,548 stars and 2,182 monthly downloads. 5 of the top 10 are actively maintained.
Get all 87 projects as JSON
curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=rag&subcategory=local-ai-workstations&limit=20"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
| # | Tool | Score | Tier |
|---|---|---|---|
| 1 |
langbot-app/LangBot
Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台. 提供... |
|
Verified |
| 2 |
open-webui/open-webui
User-friendly AI Interface (Supports Ollama, OpenAI API, ...) |
|
Verified |
| 3 |
cactus-compute/cactus
Low-latency AI engine for mobile devices & wearables |
|
Established |
| 4 |
sigoden/aichat
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools... |
|
Established |
| 5 |
rudrankriyam/Foundation-Models-Framework-Example
Example apps for Foundation Models Framework in iOS 26 and macOS 26 |
|
Established |
| 6 |
Light-Heart-Labs/DreamServer
One command to a fully local AI stack — LLM inference, chat UI, voice,... |
|
Established |
| 7 |
llama-farm/llamafarm
Deploy any AI model, agent, database, RAG, and pipeline locally or remotely... |
|
Established |
| 8 |
timmyy123/LLM-Hub
Local AI Assistant on your phone |
|
Established |
| 9 |
wangzongming/esp-ai
The simplest and lowest-cost AI integration solution. If you like this... |
|
Emerging |
| 10 |
ferranpons/Llamatik
True on-device AI for Kotlin Multiplatform (Android, iOS, Desktop, JVM,... |
|
Emerging |
| 11 |
adrianliechti/wingman
Inference Hub for AI at Scale |
|
Emerging |
| 12 |
Qingyon-AI/Revornix
拒绝FOMO!面对信息流,做个懒人,剩下的,交给AI!Reject FOMO! When facing the information stream,... |
|
Emerging |
| 13 |
dilolabs/nosia
Self-hosted AI RAG + MCP Platform |
|
Emerging |
| 14 |
Siddhesh2377/ToolNeuron
On-device AI for Android — LLM chat (GGUF/llama.cpp), vision models (VLM),... |
|
Emerging |
| 15 |
Aatricks/llmedge-examples
Examples using the llmedge library |
|
Emerging |
| 16 |
PreternaturalAI/AI
The definitive, open-source Swift framework for interfacing with generative AI. |
|
Emerging |
| 17 |
Aatricks/llmedge
Android native AI inference library, bringing gguf models and... |
|
Emerging |
| 18 |
ArtisanCloud/BrainX
BrainX 是一个智能系统,分析各种媒体格式,整合到知识库,并生成定制内容,包括机器人、洞察和媒体。它旨在为用户提供个性化和自动化的解决方案。 |
|
Emerging |
| 19 |
skye-harris/hass_local_openai_llm
Home Assistant LLM integration for local OpenAI-compatible services... |
|
Emerging |
| 20 |
KimMadsen/theMIMER
A full featured agentic, thinking, RAG enabled AI server with support for... |
|
Emerging |
| 21 |
LyzrCore/lyzr
Lyzr SDKs help you to build all your favorite GenAI SaaS products as... |
|
Emerging |
| 22 |
caixr9527/lingxi-core
无需编程,即可快速构建基于先进AI模型的各类智能应用——从简单的问答机器人到包含复杂逻辑的工作流。构建完成后,一键发布... |
|
Emerging |
| 23 |
TuringOpsSH/NextConsole
NextConsole Unleashing the Power of LLM for Enterprises |
|
Emerging |
| 24 |
caixr9527/lingxi-console
无需编程,即可快速构建基于先进AI模型的各类智能应用——从简单的问答机器人到包含复杂逻辑的工作流。构建完成后,一键发布... |
|
Emerging |
| 25 |
lm-webui/lm-webui
Unified Local AI Interface & LLM Runtime (Support GGUF, Ollama, OpenAI,... |
|
Emerging |
| 26 |
NeuroML/neuroml-ai
AI assistant for biophysically detailed neuronal modelling (NeuroML) and... |
|
Emerging |
| 27 |
debabratamishra/litemind-ui
A lightweight, open source UI for interacting with locally hosted LLMs... |
|
Emerging |
| 28 |
llamara-ai/llamara-backend
Backend of LLAMARA - the Large Language Assistant for Model-Augmented... |
|
Emerging |
| 29 |
chenking2020/my-awesome-device-llm-project
本项目旨在构造一个手机、平台等端侧设备本地运行多模态大模型能力的生态,包括运行环境、端侧大模型和前后端APP等,并追踪当前端侧大模型开源模型。This... |
|
Experimental |
| 30 |
shuyoutech/ShuYou-AI-Web
数游AI平台为您聚合了包括OpenAI、Google、Anthropic、Grok、DeepSeek、通义千问在内的众多前沿大模型。无论您面临智能对话、A... |
|
Experimental |
| 31 |
christopherkarani/MetalANNS
GPU-native approximate nearest neighbor search for Apple Silicon. Pure... |
|
Experimental |
| 32 |
eagurin/synapse
🧠 Synapse - Supercharge your AI coding assistants with memory, context, MCP... |
|
Experimental |
| 33 |
AnalyseDeCircuit/oxideterm
A Rust-native cross-platform terminal application built with Tauri 2.0,... |
|
Experimental |
| 34 |
barni007-pro/ollama_desktop_client
A feature-rich desktop GUI for Ollama with Vision, RAG, and JSON support. |
|
Experimental |
| 35 |
rish-1997/wsl-assistant
A fully auto configured, self-hosted local AI & database stack on Debian WSL2. |
|
Experimental |
| 36 |
DefinitelyN0tMe/neuralforge
Local AI workstation dashboard Neuralforge— manage LLMs, agents, RAG,... |
|
Experimental |
| 37 |
Chieko-Seren/OpenKimi
Unlimited context on any LLM ✨在任何语言模型上使用无限的上下文窗口 | 顺便一提,我们没有股权纠纷 :) |
|
Experimental |
| 38 |
undrstnd-labs/developers
Easy AI integration for devs. |
|
Experimental |
| 39 |
contractorr/stewardme
Agent that learns about you, monitors the world and tells you what to do... |
|
Experimental |
| 40 |
ai-joe-git/Belullama
Belullama is a comprehensive AI application that bundles Ollama, Open WebUI,... |
|
Experimental |
| 41 |
cozuXI/opencode_webui_cli
💻 Build and manage projects efficiently with the OpenCode Web UI CLI,... |
|
Experimental |
| 42 |
michiosw/vibe
Open-Source AI-powered web browser. Browse the web with your own LLM API... |
|
Experimental |
| 43 |
sshoecraft/shepherd
An interactive multi-backend LLM runtime with intelligent cache eviction and... |
|
Experimental |
| 44 |
DefinitelyN0tMe/ai-panel
Local AI workstation dashboard — manage LLMs, agents, RAG, Telegram AI bot... |
|
Experimental |
| 45 |
hcd233/Aris-AI-Model-Server
An OpenAI Compatible API which integrates LLM, Embedding and Reranker. 一个集成... |
|
Experimental |
| 46 |
sm1ee/openwebui-llm-proxy
OpenAI-compatible proxy for Codex CLI & Claude Code → OpenWebUI, with Qdrant... |
|
Experimental |
| 47 |
timot860/SynapseKit
Streamline neural data processing by providing tools for efficient analysis,... |
|
Experimental |
| 48 |
dev-boffin-io/ollama-forge
Local AI desktop GUI for Ollama on Linux — chat, RAG, multi-agent crews,... |
|
Experimental |
| 49 |
toy862/Qwen-Agent
Provide a customizable AI agent framework that integrates large language... |
|
Experimental |
| 50 |
TonyBucket/InsightBox
InsightBox - Hệ thống chống đứt gãy tri thức & Trợ lý học tập Đa luồng... |
|
Experimental |
| 51 |
BitWise-0x/open-webui-ultimate-stack
Production-grade Open WebUI deployment with RAG, private web search, OCR,... |
|
Experimental |
| 52 |
Nibir1/Helix
Helix: AI-powered CLI with RAG intelligence that converts natural language... |
|
Experimental |
| 53 |
iniwap/AILinkX
AILinkX 是一个连接于数字世界的独立智能体。它不依赖特定 IM... |
|
Experimental |
| 54 |
tk85457/LocalMind
Run powerful AI models entirely on your Android device. 100% offline,... |
|
Experimental |
| 55 |
Joshvareba11/model-memory-calculator
📊 Estimate memory usage for GGUF models in your browser, using local files... |
|
Experimental |
| 56 |
2501Pr0ject/RustSensei
Assistant IA local pour apprendre Rust en français. Fine-tuning LoRA sur... |
|
Experimental |
| 57 |
blib-la/ask-poddy
Ask Poddy: Run Open Source LLMs and Embeddings as OpenAI-Compatible... |
|
Experimental |
| 58 |
redten-ai/llama-client-aic
a platform for distributed, self-hosted llm rag and reinforcement learning... |
|
Experimental |
| 59 |
ualberta-rcg/vulcan-openwebui
Production-ready Kubernetes deployment for Open WebUI on the University of... |
|
Experimental |
| 60 |
Shiny-Sword/weam
Web app for teams of 20+ members. In-built connections to major LLMs via... |
|
Experimental |
| 61 |
llamara-ai/llamara-frontend
Frontend of LLAMARA - the Large Language Assistant for Model-Augmented... |
|
Experimental |
| 62 |
hztBUAA/self-host-ai
One docker-compose.yml to deploy a complete AI stack: LLM + RAG + Chat UI +... |
|
Experimental |
| 63 |
eva-foundry/11-ms-infojp
InfoJP base platform deployment |
|
Experimental |
| 64 |
py-sandy/llm-web-relay
A FastAPI gateway for local LLMs that adds intelligent web research,... |
|
Experimental |
| 65 |
abbbhucho/Ailux
A CLI that takes natural language and converts it to bash commands using a... |
|
Experimental |
| 66 |
shaharia-lab/smarty-pants
An open-source platform democratizing Generative AI Applications. Build and... |
|
Experimental |
| 67 |
Emiola033/LLM_Agent
🤖 Build a local AI agent that searches the web in real-time, ensuring... |
|
Experimental |
| 68 |
SynapseKit/synapsekit-docs
Documentation site for SynapseKit — async-first Python framework for RAG,... |
|
Experimental |
| 69 |
xueyouluo/nearly-free-wechat-bot
能自己部署的微信机器人,使用免费的大模型API |
|
Experimental |
| 70 |
dzimka/cast-ai-workbench
NVIDIA AI Hackathon app |
|
Experimental |
| 71 |
aligoraya202/FastAPI-Journal-Automation-with-Generative-And-AI-Compound-AI-System
🐙 FastAPI Journal Automation uses Gemini and Groq LLaMA to auto-create and... |
|
Experimental |
| 72 |
SithraBot/synthetic
A Kotlin-first LLM toolkit offering unified API for AI models (OpenAI,... |
|
Experimental |
| 73 |
SIC0RPS/GIA
Run local or API connected models from OpenAI, Hugging Face, or OpenRouter.... |
|
Experimental |
| 74 |
fsm-cpp/hybrid-ai-agent
An intelligent local AI agent powered by open-source LLMs, featuring free... |
|
Experimental |
| 75 |
anomaly2point0/Discord-Alternatives
Explore alternatives to Discord with a curated list of early-stage apps,... |
|
Experimental |
| 76 |
k3n37/synapse
AI platform starter for ingestion, embeddings, retrieval, and LLM orchestration |
|
Experimental |
| 77 |
isaccanedo/khoj
🍳 Your AI second brain. Self-hostable. Get answers from the web or your... |
|
Experimental |
| 78 |
kg54ktdvxx-gif/iot-intelligence-mac
macOS IoT news intelligence platform. Tauri 2 + Svelte 5 + Rust backend.... |
|
Experimental |
| 79 |
sbkocoglu/trans-aio
All-in-One Translation tool that combines Machine Translations, LLMs,... |
|
Experimental |
| 80 |
senico/aiserver
Local-AI-Cloud: High-performance, multi-GPU LLM inference server with... |
|
Experimental |
| 81 |
anton-kolyaev/vector-llm
docker compose to run agent on local |
|
Experimental |
| 82 |
dhananjay1801/Nous
An AI-powered remote command execution application for securely running... |
|
Experimental |
| 83 |
llamara-ai/llamara-deployment-docker
LLAMARA deployment using Docker |
|
Experimental |
| 84 |
llamara-ai/llamara-distro
Binary distribution of LLAMARA - the Large Language Assistant for... |
|
Experimental |
| 85 |
madkoding/neuro-ollama
Independent Ollama service for NEURO-OS ecosystem. Docker with GPU support,... |
|
Experimental |
| 86 |
feuler/openwebui-visual-retrieval
ColQwen2 local Vespa DB deploy and feed and Open-Webui retrieval function |
|
Experimental |
| 87 |
ai-khoj/khoj
Your AI second brain. Self-hostable. Get answers from the web or your docs.... |
|
Experimental |