on-prem
Projects tagged with on-prem on GitHub.
103 projects
bindwidth
JavaScriptEvidence-aware on-prem LLM inference sizing and TCO calculator
f360-vision
PowerShellSelf-hosted 3D point cloud & panorama viewer for industrial environments - free desktop app, Docker/on-premise server, or use in your browser
LocalAI
GoLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
token-diet
ShellAlways-on token-efficiency skill for coding agents (Claude Code, Codex, Cursor, Windsurf, Cline). ~31% lower bill on average, no loss of correctness.
VirtualMacOniPad
Objective-CPeople have dreamed of running macOS on iPad for more than a decade. Today, that dream comes true. With Virtual Mac, iPad finally breaks free from iPadOS, enabling pro apps like Xcode and Terminal to run directly on device. Requires iPad Pro (M1, M2) or iPad Air (M1) running iPadOS 16 up to 16.3.1.
dify
TypeScriptBuild Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
neovim
Vim ScriptVim-fork focused on extensibility and usability
voidauth
TypeScriptSingle Sign-On for Your Self-Hosted Universe
MTPLX
Python3x decode TPS increase On Qwen 3.6 27B @ temp 0.6 | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.
deltafin
PythonRun full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.
world-model-optimizer
PythonBuild continually improving models on your agent traces by distilling frontier open models
kiac
GoLocal Kubernetes on Apple's container framework - every node is its own lightweight VM. Metrics, storage, and LoadBalancer included.
ntfsmac
SwiftNTFS read/write on Apple Silicon macOS — no kernel extension, no SIP modification.
inference-school
SwiftA hands-on Swift and Metal course for building LLM inference from first principles on Apple silicon, with 48 guided lessons, runnable exercises, a native macOS Studio, and a complete companion book.
KeibiDrop
GoShare files between devices on demand. They show up as a folder on your computer, available instantly while downloading.
clash-verge-rev
TypeScriptA modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
numbat
GoVisibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.
shard
PythonPipeline-parallel LLM inference across GPUs on separate machines.
camelAI
TypeScriptcamelAI — an AI coding assistant platform built on Cloudflare Workers and Durable Objects
sakura-crossing
JavaScriptAn explorable Japanese suburban railway-crossing neighbourhood on a small planet, rendered 3D-to-2D as a cel-shaded anime background. Three.js, no image assets.
bookbag
PythonFork of Calibre-Web Focused on UI and UX improvements.
awesome-selfhosted
A list of Free Software network services and web applications which can be hosted on your own servers
aval
TypeScriptA new open-source format for interactive video on the web, with a built-in state machine, frame-accurate transitions, and packed-alpha transparency.
dao-code
TypeScriptOpen-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.
mindwalk
GoA visualization tool that replays coding-agent sessions on a 3D map of your codebase.
waku-agent
PythonWaku Waku! Waku agent is your personal AI agent, on your own laptop, in code you can read in an afternoon — harness + loop + memory + eval
gh-dashboard
TypeScriptOpen-source Git dashboard built for GIthub and Forgejo on REST and GraphQL APIs: repositories, issues, pull requests, traffic, Actions, contributors, dependents, and a kanban board view.
MLX-LoRA-Studio
SwiftA native Mac App for LLM fine-tuning on Apple Silicon — fully on-device, fully open source.
httpinspect
JavaScripttop, but for the HTTP endpoints on your host — a live dashboard of the most active plaintext HTTP endpoints, right in the terminal.
TurboVLA
PythonTurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
Noustiny
TypeScriptAn agent native video creation pipeline that runs on top of Hermes Agent
sigwire
JavaScripttail -f for signals. Every signal any process on the box raises — who sent it, who it hit, which signal, how it was raised (kill(2), the kernel, a POSIX timer), whether the target caught it and how long its handler ran, whether it tore a blocked syscall out with EINTR.
wardnet
RustWardnet is a self-hosted network privacy gateway that runs on linux (docker or bare metal). It sits alongside an existing home or small-office router, and acts as the warden of every device's connection to the internet
PowerToys
CMicrosoft PowerToys is a collection of utilities that supercharge productivity and customization on Windows
nimbus
TypeScriptDocs for humans and agents, built on Astro
rockbox-zig
CA modern, network-enabled music player platform built on Rockbox technology https://www.rockbox.org
Token-Saver
PythonA local Claude Desktop extension to query large PDFs with 92–98% fewer tokens. Performs local hybrid search, cites exact page numbers, and keeps your documents private on your machine
AutoGPT
PythonAutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
sidekick
GoBare metal to production ready in mins; your own fly server on your VPS.
agentic-inbox
TypeScriptA self-hosted email client with an AI agent, running entirely on Cloudflare Workers
beautiful-html-templates
HTMLA library of HTML slide templates designed so any coding agent can pick the right one and produce a beautiful deck on the user's behalf, automatically.
Audar-ASR-V1
PythonArabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, benchmarks & inference.
Soup
PythonFine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
yap
SwiftFree, open source voice dictation for macOS. On-device transcription with Apple's Speech framework. No cloud, no API keys, no account.
opentax-engine
JavaScriptThe deterministic tax engine for AI agents. Highest score ever recorded on TaxCalcBench (96% exact returns)
Lexicon
JavaScriptThe free open source Grammarly alternative offline writing assistant assist with grammar, rewriting & tone entirely on your machine.
bootstrap
MDXThe most popular HTML, CSS, and JavaScript framework for developing responsive, mobile first projects on the web.
HelloGitHub
Python:octocat: 分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.