Blog
Guides, comparisons, and top-lists for self-hosted AI tools.
How to Run Multi-Agent Dev Workflows with TAKT
Hands-on tutorial: install TAKT, define a plan-implement-review-fix workflow in YAML, queue tasks with /go, and run them in isolated worktrees with human checkpoints.
TAKT: YAML-Driven Orchestration for AI Coding Agents
TAKT is an open-source CLI that turns AI coding agents into repeatable workflows. Define coordination, human checkpoints, and review loops in YAML — with isolated worktrees and traceable logs.
How to Self-Host Pezzo with Docker: A Step-by-Step Guide
Learn how to deploy Pezzo, the open-source LLMOps platform, on your own server with Docker Compose — console, proxy, PostgreSQL, ClickHouse and more.
Pezzo: The Open-Source LLMOps Platform for Prompt Design and Observability
Meet Pezzo — the Apache-2.0, developer-first LLMOps platform for prompt design, Git-style versioning, instant delivery, and full observability. Self-hosted with Docker.
How to Deploy SkillHub with Docker: Step-by-Step Guide
A practical walkthrough for deploying SkillHub, the self-hosted agent skill registry, using Docker Compose — from cloning the repo to connecting Claude, Codex, and Cursor agents.
SkillHub: The Self-Hosted Agent Skill Registry for Enterprises
SkillHub from iFlytek is an open-source, self-hosted registry for AI agent skills. Learn how it brings publishing, versioning, RBAC, and audit logs to Claude, Codex, and Cursor skills — behind your firewall.
OpenMed Tutorial: De-Identify Clinical Notes with On-Device PII Redaction
Step-by-step tutorial: install OpenMed, extract drugs and conditions with the Python API, redact PII via the REST service, and scale with batch processing — all on your own hardware.
OpenMed: Local-First Healthcare AI for Clinical NER & HIPAA PII De-identification
OpenMed is a local-first healthcare AI platform for clinical NER and HIPAA PII de-identification that runs 100% on your own hardware — no cloud, no patient data leaving your network.
How to Deploy Plano with Docker: LLM Routing and Observability
Step-by-step guide to deploying Plano with Docker Compose: OpenAI-compatible LLM routing, Agentic Signals tracing, and guardrails in minutes.
Plano: The AI-Native Proxy Server for Agentic Apps
Plano is an AI-native proxy server and data plane for agentic apps: smart LLM routing, agent orchestration, observability, and guardrails built on Envoy.
How to Deploy LMCache with vLLM: Step-by-Step Tutorial
A hands-on tutorial for installing LMCache, enabling it in vLLM, running the distributed LMCache Server, and verifying time-to-first-token improvements.
LMCache: The Fastest KV Cache Layer for LLM Serving
LMCache is an open-source KV cache engine that accelerates vLLM and SGLang by reusing KV caches across requests — boosting throughput, cutting latency, and slashing LLM serving costs.
How to Deploy EdgeQuake with Docker: Step-by-Step Tutorial
Learn how to deploy EdgeQuake's GraphRAG stack with Docker in minutes — no Rust toolchain or Node.js required.
EdgeQuake: High-Performance GraphRAG in Rust — Complete Guide
Discover EdgeQuake, a Rust-based GraphRAG framework that turns documents into intelligent knowledge graphs for superior retrieval-augmented generation.
How to Deploy GPT Image Playground with Docker in 10 Minutes
Step-by-step Docker tutorial: run GPT Image Playground, connect OpenAI or any compatible provider, and generate & edit images with masks — all self-hosted.
GPT Image Playground: Self-Host Your Own OpenAI Image Studio
Meet GPT Image Playground — a polished self-hosted PWA for OpenAI gpt-image-2 with text-to-image, reference editing, mask inpainting, and local-first storage.
How to Self-Host LightX2V with Docker: Step-by-Step Setup Tutorial
Step-by-step tutorial to deploy LightX2V, the lightweight image, video and action generation framework, using the official Docker image — including health checks and tuning tips.
LightX2V: A Lightweight Inference Framework for Image, Video & Action Generation
Meet LightX2V — the Apache-2.0 inference framework from ModelTC that unifies Open-Sora, Stable Diffusion, AnimateDiff and CogVideoX behind one lightweight, self-hostable API.
How to Scan Your LLM Agent for Vulnerabilities with Giskard: Step-by-Step Tutorial
A hands-on tutorial: run Giskard with Docker, upload your model, scan for prompt injection and hallucinations, and deploy auto-generated tests to CI/CD.
Giskard Guide: Open-Source Testing & Evaluation for LLM Agents
Learn how Giskard scans LLM agents for hallucinations, prompt injection and data leakage, and auto-generates domain-specific test suites for reliable AI.