Self-Hosted AI

Local AI chat UIs, self-hosted companions, own-your-AI platforms, and private agents

165 explainers
Memos: The Architecture of Instant Capture
Self-Hosted AI
Memos: The Architecture of Instant Capture
How a single Go binary turned the high-friction "knowledge base" into a private, high-velocity stream of consciousness.
7 min read
Appwrite and the Art of the Self-Hosted Cloud
Self-Hosted AI
Appwrite and the Art of the Self-Hosted Cloud
How a high-performance PHP core and a fleet of Docker microservices turned the Firebase alternative into a portable infrastructure powerhouse.
Odysseus: The Self-Hosted AI Workspace That Tries to Be Your Private Operating System
Self-Hosted AI
Odysseus: The Self-Hosted AI Workspace That Tries to Be Your Private Operating System
A deep look at a project that connects local model serving, model selection, research, memory, and everyday work into one workspace.
8 min read
The Database That Rewrote C++: Inside ClickHouse
Self-Hosted AI
The Database That Rewrote C++: Inside ClickHouse
How an obsession with mechanical sympathy and a custom standard library built the engine behind the world's largest analytical workloads.
8 min read
Cal.diy: The Fork That Makes Cal.com Smaller, Cleaner, and Free to Self-Host
Self-Hosted AI
Cal.diy: The Fork That Makes Cal.com Smaller, Cleaner, and Free to Self-Host
A close look at the subtractive fork that strips out enterprise bloat, preserves the scheduling core, and turns a commercial codebase into a practical DIY stack.
11 min read
worldmonitor: The Open-Source Palantir Running in Your Browser
Self-Hosted AI
worldmonitor: The Open-Source Palantir Running in Your Browser
How koala73/worldmonitor ditched heavy frameworks to render massive geopolitical data streams at 60 frames per second.
8 min read
Escaping the Vendor Prison: Unpacking LizardByte/Sunshine
Self-Hosted AI
Escaping the Vendor Prison: Unpacking LizardByte/Sunshine
How a community-driven C++ server replaced NVIDIA GameStream by combining low-level OS hooks with ruthless performance threading.
8 min read
deepseek-harness-desktop: When the Desktop Becomes a Plugin
Self-Hosted AI
deepseek-harness-desktop: When the Desktop Becomes a Plugin
A native Electron shell that treats the UI, installer, marketplace, and recovery path as part of the same modular system.
9 min read
Onyx: The Open-Source AI Platform That Turns Company Data Into Agentic Context
Self-Hosted AI
Onyx: The Open-Source AI Platform That Turns Company Data Into Agentic Context
A self-hosted stack for enterprise search, deep research, and tool-using assistants, built to move beyond simple RAG and into real context orchestration.
9 min read
The SQLite Mirror: Inside Duplicati's Zero-Knowledge Engine
Self-Hosted AI
The SQLite Mirror: Inside Duplicati's Zero-Knowledge Engine
How a C# backup client brings enterprise-grade deduplication to the masses, and the architectural price of keeping a local index of the cloud.
8 min read
Floci: The Native Java AWS Emulator Built for the Post-LocalStack Era
Self-Hosted AI
Floci: The Native Java AWS Emulator Built for the Post-LocalStack Era
A fast, MIT-licensed local AWS stack that trades feature gates for real containers, compatibility testing, and a surprising amount of Java performance.
9 min read
EmDash CMS: The WordPress-Style CMS That Jails Its Plugins
Self-Hosted AI
EmDash CMS: The WordPress-Style CMS That Jails Its Plugins
Cloudflare’s TypeScript CMS rebuilds the classic CMS contract around isolated workers, explicit capabilities, and structured content.
9 min read
ReClip: The Tiny Self-Hosted Wrapper That Makes `yt-dlp` Feel Like a Product
Self-Hosted AI
ReClip: The Tiny Self-Hosted Wrapper That Makes `yt-dlp` Feel Like a Product
A single-file Flask backend, a vanilla HTML frontend, and a surprisingly polished workflow for bulk media downloads without the SaaS junk.
8 min read
cog: The Death of the Hand-Written ML Dockerfile
Self-Hosted AI
cog: The Death of the Hand-Written ML Dockerfile
How a Go-based expert system and a high-performance Rust orchestrator eliminated "CUDA hell" and standardized machine learning deployment.
8 min read
local-deep-research: Local Deep Research: The Private Research Agent That Knows When to Keep Digging
Self-Hosted AI
local-deep-research: Local Deep Research: The Private Research Agent That Knows When to Keep Digging
A local-first deep research system that combines strategy-switching agents, encrypted memory, and source-quality filtering to produce serious research without sending your data to the cloud.
9 min read
G0DM0D3: The AI Chat Interface That Treats LLMs Like Test Subjects
Self-Hosted AI
G0DM0D3: The AI Chat Interface That Treats LLMs Like Test Subjects
A self-hostable research cockpit that perturbs prompts, races models in parallel, scores the contenders, and cleans up the result into a more controlled voice.
9 min read
The Dockerization of iOS: Inside vphone-aio
Self-Hosted AI
The Dockerization of iOS: Inside vphone-aio
How a single shell script bypasses Apple's hardware locks to spin up a jailbroken iOS virtual machine on Apple Silicon.
6 min read
AIHOT: The Open-Source Newsroom That Learns What Matters
Self-Hosted AI
AIHOT: The Open-Source Newsroom That Learns What Matters
A self-hosted framework for turning noisy industry feeds into scored, clustered, agent-readable daily briefings.
10 min read
obsidian-copilot: The Portable Agent Runtime Hidden Inside Your Notes
Self-Hosted AI
obsidian-copilot: The Portable Agent Runtime Hidden Inside Your Notes
A deep dive into the Obsidian plugin that turns vault search, tool calling, and model switching into one local-first AI workflow.
10 min read
noctalia-shell: Noctalia Shell: The Wayland Desktop That Treats Your Config Like Software
Self-Hosted AI
noctalia-shell: Noctalia Shell: The Wayland Desktop That Treats Your Config Like Software
A deep look at the shell layer that hot-reloads settings, migrates old configs, animates themes globally, and makes a modular Linux desktop feel durable instead of fragile.
9 min read
PilotDeck: The Agent OS That Treats Memory, Files, and Background Work as First-Class Citizens
Self-Hosted AI
PilotDeck: The Agent OS That Treats Memory, Files, and Background Work as First-Class Citizens
A close look at the open-source system pushing beyond chat into persistent WorkSpaces, white-box memory, smart routing, and always-on execution.
9 min read
WechatOnCloud: The Docker Layer That Turns WeChat Into a Managed Service
Self-Hosted AI
WechatOnCloud: The Docker Layer That Turns WeChat Into a Managed Service
A deep dive into the project that keeps official WeChat running in disposable containers, proxies the session through the browser, and adds the kind of self-healing logic homelab users actually need.
9 min read
EhViewer-NekoInverter/EhViewer: The Android Client That Turns a Messy Website Into a Native Library
Self-Hosted AI
EhViewer-NekoInverter/EhViewer: The Android Client That Turns a Messy Website Into a Native Library
A deep look at the hybrid parsers, native archive pipeline, and session-handling tricks that let a legacy fork behave like a high-performance gallery app.
9 min read
Inside `grok-bot-0.18-reconstructed`: The Shell That Let Grok Bot Speak to Other Models
Self-Hosted AI
Inside `grok-bot-0.18-reconstructed`: The Shell That Let Grok Bot Speak to Other Models
A contract-first rebuild of a proprietary Electron app, with readable TypeScript, a preserved frontend shape, and a backend that can route through Claude Code, Codex, or OpenRouter.
10 min read
FDE-the-Guidance-Book-of-Forward-Deployed-Engineer: The Manual for Turning AI Demos into Enterprise Systems
Self-Hosted AI
FDE-the-Guidance-Book-of-Forward-Deployed-Engineer: The Manual for Turning AI Demos into Enterprise Systems
A Chinese open-source playbook for the engineer who sits between messy real-world operations, legacy data, and the product team that has to learn from both.
11 min read
agent-os: agentOS: The OS for AI Agents That Runs Inside Your Backend
Self-Hosted AI
agent-os: agentOS: The OS for AI Agents That Runs Inside Your Backend
A Rust kernel, Wasm execution plane, and deny-by-default permissions model replace the heavy container stack with something faster, denser, and built for untrusted agent code.
10 min read
Roots Trellis: The WordPress Stack That Treats Environments Like Code
Self-Hosted AI
Roots Trellis: The WordPress Stack That Treats Environments Like Code
Ansible, Lima VMs, Nginx, and zero-downtime deploys combine into one opinionated system that keeps local development, staging, and production aligned.
8 min read
Siftly: The Local AI Layer That Turns X Bookmarks Into a Searchable Knowledge Base
Self-Hosted AI
Siftly: The Local AI Layer That Turns X Bookmarks Into a Searchable Knowledge Base
A self-hosted, multimodal bookmark engine that extracts meaning from text, images, and metadata, then keeps the whole thing private in SQLite.
8 min read
S3-Uploads: The WordPress Plugin That Makes S3 Feel Like a Local Disk
Self-Hosted AI
S3-Uploads: The WordPress Plugin That Makes S3 Feel Like a Local Disk
A deep look at the stream-wrapper trick, the no-UI philosophy, and the infrastructure decisions that let WordPress media live on object storage without turning the rest of the app upside down.
10 min read
Mike: The Open-Source Legal AI That Writes Redlines, Not Just Drafts
Self-Hosted AI
Mike: The Open-Source Legal AI That Writes Redlines, Not Just Drafts
An inside look at the document engine, multi-model orchestration, and citation system that make this platform feel built for lawyers instead of demo users.
9 min read
WeChat-AI Turns WeChat Into an Operating System for AI Personas
Self-Hosted AI
WeChat-AI Turns WeChat Into an Operating System for AI Personas
A self-hosted, multi-node framework that bridges Tencent’s iLink protocol, Redis-backed memory, Chatflow orchestration, and human-like reply behavior to make bots feel persistent, social, and surprisingly alive.
9 min read
Zarf: The Package Manager That Freezes Kubernetes for the Air Gap
Self-Hosted AI
Zarf: The Package Manager That Freezes Kubernetes for the Air Gap
A deep dive into the tool that bundles images, charts, signatures, and cluster bootstrapping into one portable artifact, so connected development can become disconnected deployment without rewriting everything by hand.
12 min read
exhentai-manga-manager: The Offline Library That Thinks Like E-Hentai
Self-Hosted AI
exhentai-manga-manager: The Offline Library That Thinks Like E-Hentai
A local-first Electron app that scans archives, extracts covers, maps tags, and makes a private manga collection search like a live metadata service.
8 min read
Agentic Coding Flywheel Setup: Building an OS for AI
Self-Hosted AI
Agentic Coding Flywheel Setup: Building an OS for AI
How a declarative shell architecture turns a raw Ubuntu VPS into a high-velocity, self-healing factory for autonomous coding agents.
9 min read
LearnHouse: The Headless Architecture of Modern Education
Self-Hosted AI
LearnHouse: The Headless Architecture of Modern Education
How a modern Python stack uses granular JSON blocks and vector embeddings to replace the legacy LMS monolith.
7 min read
Omni: The Bare-Metal Control Plane That Makes Hardware Feel Like an API
Self-Hosted AI
Omni: The Bare-Metal Control Plane That Makes Hardware Feel Like an API
A deep dive into how Sidero Labs combines Talos, signed gRPC, and outbound tunnels to manage Kubernetes clusters on machines you cannot directly reach.
9 min read
Unrud/video-downloader: The GNOME App That Hides yt-dlp’s Chaos Behind One Clean Click
Self-Hosted AI
Unrud/video-downloader: The GNOME App That Hides yt-dlp’s Chaos Behind One Clean Click
A deep dive into the slave-process architecture, state-driven UI, and packaging tricks that make a video downloader feel native instead of fragile.
8 min read
`undress-service`: The Repo That Looks Like a Wardrobe App and Behaves Like Two Projects
Self-Hosted AI
`undress-service`: The Repo That Looks Like a Wardrobe App and Behaves Like Two Projects
A self-hosted FastAPI fashion assistant, a local AI styling stack, and a completely separate downloader package living in the same tree.
8 min read
NorthCinder: The Shopping Agent That Refuses to Trust the Marketplace
Self-Hosted AI
NorthCinder: The Shopping Agent That Refuses to Trust the Marketplace
A local MCP server for agentic commerce, built around deterministic ranking, human approval, and audit trails that keep the buyer in control.
9 min read
Tropy: The Desktop App That Turns Research Photos Into Structured Evidence
Self-Hosted AI
Tropy: The Desktop App That Turns Research Photos Into Structured Evidence
Inside the local-first archive tool that blends Electron, SQLite, Pixi.js, and linked data to help historians organize, describe, and preserve primary sources.
9 min read
x4gKing/3x-ui-Upgrade: How One Port Becomes a VPN Panel, a Subscription Feed, and a Front Door
Self-Hosted AI
x4gKing/3x-ui-Upgrade: How One Port Becomes a VPN Panel, a Subscription Feed, and a Front Door
A Docker wrapper, Nginx router, and just-in-time startup script collapse a multi-port Xray workflow into a single PaaS-friendly deployment.
8 min read
wechatpay: WeChat Bill Analyzer Turns Export Chaos Into a Private Financial X-Ray
Self-Hosted AI
wechatpay: WeChat Bill Analyzer Turns Export Chaos Into a Private Financial X-Ray
A lean Electron app that finds the real table inside messy WeChat Pay spreadsheets, checks the totals, and turns local-only financial data into usable insight.
8 min read
Inside openai/openai-chatkit-starter-app: The Chat Starter That Makes the Backend a Boundary
Self-Hosted AI
Inside openai/openai-chatkit-starter-app: The Chat Starter That Makes the Backend a Boundary
A deep dive into OpenAI’s reference app, where one path hosts the whole conversation and the other turns the server into a secure session broker.
11 min read
hermes-webui: Hermes WebUI: The Browser Shell for a Living Agent
Self-Hosted AI
hermes-webui: Hermes WebUI: The Browser Shell for a Living Agent
A no-framework, zero-build interface that gives Hermes a Claude-style home in the browser without breaking the CLI-first, persistent-state model underneath.
8 min read
Automattic/studio: The End of the Local LAMP Stack
Self-Hosted AI
Automattic/studio: The End of the Local LAMP Stack
How WebAssembly, SQLite, and a custom TypeScript daemon turned a heavyweight CMS into an instant-on application with a self-correcting AI agent.
8 min read
paid-memberships-pro: Paid Memberships Pro: The WordPress Plugin That Turns Payment Chaos Into One Membership Engine
Self-Hosted AI
paid-memberships-pro: Paid Memberships Pro: The WordPress Plugin That Turns Payment Chaos Into One Membership Engine
A deep look at the gateway translator, the legacy-safe order model, and the defensive coding that lets a 2011 plugin keep evolving without breaking old sites.
10 min read
sandboxd: The Anti-Kubernetes Engine Behind Sleeping Sandboxes and Live Preview URLs
Self-Hosted AI
sandboxd: The Anti-Kubernetes Engine Behind Sleeping Sandboxes and Live Preview URLs
A single Go daemon, SQLite, Docker, and Traefik power a self-hosted sandbox platform that wakes containers on demand, reaps them under memory pressure, and keeps AI app builders cheap enough to run on one box.
9 min read
BunkerM: The "Fat Sidecar" That Hardens the IoT Edge
Self-Hosted AI
BunkerM: The "Fat Sidecar" That Hardens the IoT Edge
How a containerized security layer transformed Eclipse Mosquitto from a silent broker into a managed, anomaly-detecting gateway.
8 min read