Open-source. Self-hostable. No API keys required.
Find the right open-source AI tool.
Honest reviews and comparisons of open-source AI tools — LLM runners, image generators, coding assistants, and self-hosted stacks. No hype, just what works.
What we cover
Four categories of open-source AI tooling.
-
LLM Runners
Ollama, llama.cpp, LM Studio, vLLM, Tabby — what each does best and which one fits your setup.
-
Image Generation
ComfyUI, Automatic1111, InvokeAI, Fooocus — feature comparisons, workflow depth, and ease-of-use tradeoffs.
-
Coding Assistants
Continue.dev, Cline, Aider, Tabby — open-source alternatives to Copilot that run on your own models.
-
Self-Hosted Stack
Open WebUI, Flowise, n8n, Langfuse — the glue layer that turns individual tools into a working AI stack.
Latest posts
Fresh from the bench.
-
Inkling-Small Self-Hosting Guide 2026: Run 276B on One GPU
How to self-host Inkling-Small with llama.cpp and vLLM: Apache 2.0 license check, Unsloth GGUF sizes from 75GB, and which hardware tier actually fits it.
Read guide → -
NVMe KV Cache Offloading for vLLM and Ollama in 2026: The Honest Long-Context Setup Guide
How to spill LLM KV cache to an NVMe SSD with vLLM + LMCache, why Ollama can't do it yet, and why the viral 'Kimi K3 at 1M context on a consumer GPU' claim doesn't survive the math.
Read guide → -
MCP Stateless Spec 2026: Migrate Your Self-Hosted Servers
The 2026-07-28 MCP spec removes sessions and the initialize handshake. What breaks in self-hosted n8n, Flowise, and Open WebUI stacks — and how to migrate.
Read guide → -
EUROPA 400B: The EU's Open-Source Frontier Model, and What Self-Hosters Should Watch
The EU picked the Domyn-led EUROPA consortium to build a 400B+ open-source MoE model in all 24 EU languages. License, VRAM estimates, and what to run today.
Read guide → -
LM Studio MLX Engine 1.8.5: KV Cache Checkpointing Guide
LM Studio's mlx-engine 1.8.5 cuts agentic RAM use up to 80% on Apple Silicon with KV cache checkpointing. Setup, API wiring, and honest limits.
Read guide →