Self-Hosted Platforms

Open-source GPU control plane for scalable AI model serving

Open-source GPU cluster manager that configures vLLM, SGLang, TensorRT-LLM or custom engines, serves models through compatible APIs, and provisions SSH-accessible GPU instances across on-premises, Kubernetes and cloud environments.

Cloud-native POSIX filesystem on object storage

JuiceFS is a high-performance distributed POSIX filesystem built on object storage like S3 and metadata engines like Redis or MySQL. It enables seamless data sharing across thousands of clients with low latency and elastic throughput. JuiceFS ships with a Kubernetes CSI driver, Hadoop SDK compatibility, and FUSE mount support for AI training, big data analytics, and shared storage workloads. Apache 2.0 licensed with 13K+ GitHub stars.

Deploy web apps anywhere

Zero-downtime deployment tool created by 37signals (Basecamp/HEY) that deploys Docker containers to any VPS or bare metal server over SSH without requiring Kubernetes. Manages rolling deploys, health checks, SSL via Let's Encrypt, container registry, and load balancing with Traefik. Simple YAML-based config. Ideal for small teams deploying Rails, Node.js, or any Dockerized app. Ships as a Ruby gem. 12K+ GitHub stars and a growing alternative to complex container orchestration.

Open-source AI second brain with deep research and RAG

Khoj is an open-source personal AI app that serves as a self-hostable second brain. It connects to your documents — PDFs, Markdown, Notion, Word — and uses RAG to answer questions grounded in your knowledge base. Supports any local or cloud LLM including Llama, Claude, GPT, and Gemini. Features custom agents, scheduled automations, deep research mode, semantic search, and Obsidian, Emacs, and WhatsApp integrations. Over 33,000 GitHub stars, YC-backed.

RAG-based document QA with multi-user support and agent reasoning

Kotaemon is an open-source RAG-powered document question-answering interface backed by Cinnamon AI. It supports multi-user workspaces with access controls, advanced retrieval pipelines including hybrid search and knowledge graph extraction, and agentic reasoning for complex multi-step queries. The web UI handles PDFs, Office documents, and images with citations pointing to exact source passages, making it suitable for both individual research and team knowledge management.

Open-source toolkit for quantizing, deploying, and serving LLMs and vision-language models

LMDeploy is an Apache-2.0 toolkit for self-hosting LLM and vision-language model inference with TurboMind and PyTorch engines. It combines continuous batching, blocked KV cache, tensor parallelism, AWQ and KV-cache quantization with OpenAI-compatible APIs, multi-GPU distribution, offline pipelines, and production metrics.

Build custom AI inference servers in pure Python

Open-source, FastAPI-based serving engine from Lightning AI for building custom inference APIs — models, agents, RAG, and pipelines — with built-in batching, streaming, and multi-GPU autoscaling.

Google's production on-device LLM inference framework

LiteRT-LM is Google's official open-source framework for running large language models on-device across Android, iOS, Web, Desktop, and Raspberry Pi. Already deployed in Chrome and Pixel hardware, it provides production-grade on-device LLM inference with 1.4K+ GitHub stars. Apache 2.0 licensed.

macOS and Linux VM runtime for AI agents on Apple Silicon

Lume is an open-source CLI for creating and managing macOS and Linux virtual machines on Apple Silicon, built specifically for AI agent sandboxing, CI/CD pipelines, and desktop automation. Using Apple's native Virtualization.Framework for near-native performance, it provides the missing isolation layer for running coding agents safely — so an accidental destructive command doesn't affect your host machine.

Run and fine-tune Vision Language Models locally on Mac

Open-source Python package for running and fine-tuning Vision Language Models locally on Mac using Apple's MLX framework. Supports multimodal inference with images, audio, and video across Qwen, DeepSeek, Phi, and Gemma architectures. Features OpenAI-compatible API server, Gradio chat UI, and KV cache optimization. 3.8K+ GitHub stars.

Enterprise-grade RAG and MCP knowledge base with one-click deployment

MaxKB is an enterprise-grade RAG platform with 21,000+ GitHub stars from the 1Panel team. It provides one-click deployment of knowledge bases with built-in LLM integration, MCP support, and a streamlined approach to document ingestion and retrieval that prioritizes operational simplicity over configuration complexity.

Free MIT-licensed drop-in replacement for LocalStack

MiniStack is a free, MIT-licensed drop-in replacement for LocalStack that emulates 33 AWS services using real infrastructure — actual Postgres for RDS, real Redis for ElastiCache, real Docker for ECS — rather than faking API responses. Born from LocalStack's surprise paywall in March 2026, it starts in 2 seconds, idles at 30MB RAM versus LocalStack's ~500MB, and runs real services for accurate local AWS development.

Disaggregated KV cache storage and transfer for LLM serving

Open-source infrastructure for disaggregated LLM serving that pools KV caches across prefill and decode workers, with high-performance transfer, distributed storage and integrations for vLLM and SGLang.

Open-source zero-trust networking with WireGuard

NetBird is an open-source zero-trust networking platform that creates encrypted WireGuard overlay networks between devices without opening ports or configuring firewalls. It provides peer-to-peer connectivity with NAT traversal, access control policies, DNS management, and a web dashboard for team management. NetBird replaces traditional VPNs with a simpler, more secure mesh networking approach for self-hosted infrastructure and remote teams.

Cross-platform on-device AI model runtime

Nexa SDK enables running frontier LLMs and multimodal models locally across PC, mobile, IoT, and wearables with automatic hardware acceleration for GPU, NPU, and CPU. It supports Qwen, Gemma, Llama, DeepSeek models with Python/C++ desktop SDKs, Android/iOS mobile SDKs, and Docker for edge deployment. Includes an OpenAI-compatible API server with chat and function calling support.

Extensibility-first open-source no-code/low-code platform for business apps

NocoBase is an open-source, self-hosted no-code and low-code platform built around a data-model-driven architecture and plugin-based microkernel. Unlike form-centric no-code tools, it separates data structure from UI, enabling unlimited block types and views per data collection. All functionality is delivered through plugins similar to WordPress. Features include AI Employees for in-app automation, visual workflow builder, RBAC permissions, and automatic REST/GraphQL API generation.

Low-code visual programming for event-driven apps

Node-RED is a flow-based, low-code development tool originally created by IBM in 2013 for wiring together hardware devices, APIs, and online services. Now an OpenJS Foundation project with nearly 23,000 GitHub stars, it provides a browser-based visual editor where flows are built by dragging and connecting nodes, then deployed to the Node.js runtime in a single click. Over 5,000 community-contributed nodes cover protocols like MQTT, Modbus, and OPC-UA alongside cloud APIs and databases.

OpenAI API management gateway for 100+ LLM providers

One API is a self-hosted LLM API gateway that provides a unified OpenAI-compatible interface for managing multiple model providers including OpenAI, Azure, Anthropic, Google, and dozens of Chinese providers. It handles load balancing, quota management, rate limiting, token tracking, and channel-based routing through a web dashboard. Widely adopted in the Chinese developer ecosystem with over 18,000 GitHub stars.

Private, self-hosted research notebooks with flexible AI models, source chat, and podcasts

Open Notebook is an MIT-licensed, self-hosted alternative to NotebookLM for collecting sources, chatting over research, generating reusable transformations, and producing multi-speaker podcasts. Its Docker stack keeps notebook data under the user's control while supporting 18-plus model providers, including local Ollama and LM Studio workflows.

Local-first personal AI agent with memory trees, desktop integrations, and private workspace context.

OpenHuman is an open-source, local-first personal AI agent from TinyHumans. It combines a desktop app, persistent memory trees, Obsidian-compatible storage, OAuth integrations, and local model support into a private assistant harness. It is most interesting for users who want agentic workflows and long-term memory without handing every context detail to a fully cloud-hosted assistant.

Open-source TypeScript headless CMS and app framework

Payload is an open-source TypeScript-first headless CMS and app framework with 32K+ GitHub stars. Built on Next.js with PostgreSQL or MongoDB, it provides auto-generated REST and GraphQL APIs, a customizable admin panel, access control, localization, versioning, and file uploads. Config-as-code defines collections in TypeScript for full type safety. Features live preview, draft system, block-based editor, and extensible plugins. Self-hostable with no vendor lock-in.

Single-binary open-source backend

PocketBase is an open-source backend in a single Go binary with 44K+ GitHub stars providing a real-time database, authentication, file storage, and admin dashboard. No dependencies, no Docker required — just download and run. Features collection-based data modeling, REST API, real-time subscriptions, OAuth2 authentication, file uploads with thumbnails, and a built-in admin UI. Extends with custom Go code or JavaScript hooks. Ideal for prototyping, MVPs, and small-to-medium applications.

Daemonless container engine — a drop-in Docker alternative that runs rootless.

Podman is a daemonless, open-source container engine developed by Red Hat as a secure alternative to Docker. It can run, build, and manage OCI containers and pods without requiring a daemon process or root privileges. CLI-compatible with Docker commands, making migration seamless.

Container management GUI for Docker and Kubernetes

Portainer is an open-source container management platform with 32K+ GitHub stars providing a web-based GUI for Docker, Docker Swarm, and Kubernetes. Simplifies container operations with visual management of containers, images, volumes, networks, and stacks without CLI expertise. Features user management with RBAC, environment templates, GitOps deployments, and edge computing support. Community Edition is free for up to 5 environments. Business Edition adds governance and support.

Heroku-like PaaS built on Kubernetes with YC backing

Porter is a YC-backed platform-as-a-service that provides a Heroku-like deployment experience on top of Kubernetes. It abstracts away cluster management while giving teams full access to underlying infrastructure when needed. Supports deploying from Git repos, Docker images, or Helm charts with automatic HTTPS, scaling, and preview environments. Runs on AWS, GCP, or Azure.

First commercially viable 1-bit LLMs that are 14x smaller and 8x faster

PrismML Bonsai delivers the first commercially viable 1-bit large language models with 8B, 4B, and 1.7B parameter variants. The 8B model runs in just 1GB of RAM versus 16GB for standard FP16 models, achieving 44 tokens per second on iPhone. Backed by $16.25M from Khosla Ventures and released under Apache 2.0, Bonsai makes capable LLMs practical for edge devices and resource-constrained environments.

Container-native local AI model serving with Podman

RamaLama is an open-source tool that containerizes AI model inference using Podman or Docker, eliminating host system configuration complexity. It auto-detects GPUs (NVIDIA, AMD, Intel, Apple Silicon), pulls models from HuggingFace, Ollama, and OCI registries, and runs them in isolated rootless containers with read-only mounts and network isolation. Developed under the Containers project (Red Hat ecosystem), it brings familiar container workflows to local LLM serving.

Kafka-compatible streaming platform, no JVM required

Redpanda is a Kafka-compatible streaming data platform written in C++ using the Seastar framework. It eliminates the need for ZooKeeper and the JVM, delivering up to 10x lower tail latencies and significantly reduced operational complexity. Redpanda ships as a single binary with a built-in schema registry, HTTP proxy, and message broker. It supports the Kafka wire protocol, so existing producers, consumers, and tools work without code changes. Backed by $165M+ in funding with 12.0K GitHub stars.

High-performance S3-compatible object storage built in Rust

RustFS is an open-source distributed object storage system built entirely in Rust, offering 2.3x faster performance than MinIO for small object payloads. It provides full S3 API compatibility, enabling seamless migration from MinIO, Ceph, and AWS S3 with existing SDKs and CLI tools. Released under Apache 2.0 license, it avoids MinIO's restrictive AGPL terms. Features include distributed architecture, erasure coding, WORM compliance, encryption via RustyVault, and a web management console.

Self-hosted UI and API for Ansible, Terraform, and scripts

Semaphore UI provides a web interface and REST API for running Ansible playbooks, Terraform and OpenTofu configurations, Bash scripts, and PowerShell commands from a centralized self-hosted platform. With over 13,000 GitHub stars and 2 million Docker pulls, it replaces AWX and manual terminal execution with a polished dashboard for scheduling, access control, notifications, and execution history across mixed infrastructure automation environments.

Self-hosted code understanding for humans and agents

Sourcebot is a self-hosted code intelligence platform that helps developers and AI agents understand large codebases through intelligent search, navigation, and inline-cited answers. Deployed as a Docker container with MCP server support, it indexes thousands of repositories without source code leaving your infrastructure.

Open-source headless CMS for developers

Strapi is the leading open-source headless CMS with 65K+ GitHub stars providing a customizable API-first content management system. Auto-generates REST and GraphQL APIs from content types defined through a visual builder. Features role-based access control, media library, internationalization, draft/publish workflow, and a plugin marketplace. Built with Node.js and supports PostgreSQL, MySQL, SQLite, and MariaDB. Self-hostable with Strapi Cloud also available.

Enterprise internal app platform with AI generation

Superblocks is an enterprise internal application platform that uses AI to automate backend integrations and UI generation for high-performance internal tools. It targets pro-developer teams who need more control than typical low-code platforms provide, offering code-level customization alongside visual building with enterprise features like SSO, audit logs, and fine-grained permissions.

Self-hosted AI accounting for freelancers and small teams

TaxHacker is an open-source, self-hosted AI accounting app that automatically extracts financial data from receipts, invoices, and bank statements using LLMs. It supports 170+ currencies and 14 cryptocurrencies with historical exchange rate conversion, multi-project accounting, and custom AI extraction fields. Works with OpenAI, Gemini, Mistral, or local models via Ollama—deploy with Docker and keep all financial data under your control.

Enterprise feature platform for real-time ML

Tecton is an enterprise feature platform for building and serving ML features at scale. Created by the team behind Feast, it provides managed feature engineering, real-time feature computation from streaming data, feature monitoring, and a unified feature store with offline/online consistency. Used by production ML teams to eliminate training-serving skew and accelerate model deployment cycles.

Self-hosted SSH and server management platform

Termix is a self-hosted SSH and server management platform that provides a modern web-based terminal, connection management, SFTP file transfer, and multi-device sync without subscription fees. It serves as an open-source alternative to Termius, offering team collaboration features, connection sharing, and a clean interface for managing SSH connections across servers, all deployable via Docker.

Hugging Face's open-source inference server for embeddings, rerankers, and classifiers

Text Embeddings Inference is Hugging Face's Apache-2.0 server for high-throughput embedding, reranking, and sequence-classification models. TEI packages token-based dynamic batching, optimized Transformers kernels, Safetensors loading, OpenAI-compatible embedding endpoints, Prometheus metrics, and configurable OpenTelemetry tracing in deployable CPU and GPU images.

Low-code AI platform for internal tools with RBAC

UI Bakery AI is a low-code platform with AI assistance specifically for building production-ready internal tools, featuring enterprise-grade RBAC, SSO integration, and SOC 2 compliance. It combines visual app building with AI-powered code generation for complex business logic, targeting internal operations teams who need admin panels and dashboards with proper security controls.

Lightweight microVM execution layer for AI agent code sandboxing

Vercel Sandbox provides a lightweight microVM execution environment for running untrusted code generated by AI agents safely. It creates isolated sandboxes that prevent generated code from accessing the host system, network, or other processes. Designed for AI coding platforms that need to execute user or agent-generated code without security risks to the host infrastructure.

High-performance WebAssembly runtime for cloud and AI

WasmEdge is a CNCF sandbox WebAssembly runtime optimized for cloud-native, edge, and AI workloads. It provides a lightweight, secure, and portable execution environment that is faster than containers and safer than native processes. WasmEdge supports LLM inference via LlamaEdge, serverless functions, microservices, and plugin extensions for networking, AI, and cryptography across Linux, macOS, and Windows.

Batteries-included full-stack framework for React, Node.js, and Prisma

Wasp is an open-source full-stack web framework that brings the Rails-like batteries-included experience to the JavaScript ecosystem. It uses a declarative configuration file to define auth, database models, server operations, and routing, then compiles to a standard React and Node.js application with Prisma for data access. With 18,000+ GitHub stars and YC backing, Wasp eliminates boilerplate while giving AI coding agents clear structure and guardrails.

Lightweight self-hosted CI/CD engine for the Gitea stack

Woodpecker CI is a community-maintained open-source CI/CD engine forked from Drone CI, designed as the default continuous integration solution for self-hosted Git platforms like Gitea, Forgejo, and Codeberg. With simple YAML pipeline configuration, minimal resource usage (~100MB RAM), and Apache-2.0 licensing, it provides a lightweight alternative to Jenkins and GitHub Actions for developers who prefer infrastructure they control.

Desktop hub for managing all your server connections

XPipe is an open-source desktop application that centralizes access to your entire server infrastructure through a unified interface. It connects to remote systems via SSH, Docker containers, Kubernetes clusters, LXC, and virtual machines — eliminating context switching between multiple terminal sessions and infrastructure tools without requiring any remote-side setup or installation.

Lightweight OS for running AI agents in-process

agentOS is a portable open-source operating system for AI agents that delivers ~6ms cold starts at 32x lower cost than traditional sandboxes. Powered by WebAssembly and V8 isolates, it runs agents like Claude Code and Codex directly inside your process with granular permissions and host-managed tool access for S3, GitHub, and databases. Available as a simple npm package with no special infrastructure or vendor lock-in required.

One-command local coding agent that auto-detects your hardware and picks the best model

hf-agents is a Hugging Face CLI extension that detects your hardware, recommends the best GGUF model using llmfit, and launches a local coding agent in a single command. It collapses the multi-step local LLM setup into hf agents run pi, automatically handling hardware profiling, model download, inference server startup, and coding agent activation.

Hot-swap between local LLM models via OpenAI-compatible API

llama-swap is an open-source tool that manages multiple local LLM models behind a single OpenAI-compatible API endpoint. It automatically loads and unloads models on demand, letting developers hot-swap between different models without restarting services. With 3.1K+ GitHub stars, it solves the common pain point of running multiple specialized models on limited hardware.

Find which AI models actually run on your hardware in one command

llmfit is a Rust-based terminal tool that matches over 200 LLM models from 30+ providers against your exact hardware specs. The interactive TUI scores each model on fit, speed, VRAM usage, and context length, helping you avoid downloading models that won't run on your machine. It supports Ollama, llama.cpp, MLX, Docker Model Runner, and LM Studio backends.

Lightweight virtual Kubernetes clusters

vCluster creates lightweight, isolated virtual Kubernetes clusters inside physical host clusters, enabling teams to run sandboxed environments for development, testing, and AI agent experimentation without provisioning separate infrastructure. Each virtual cluster has its own API server, control plane, and resource isolation while sharing the underlying compute, reducing infrastructure costs by up to 90% compared to full cluster provisioning.