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.
-
Hugging Face dry run: budget disk before model downloads
Plan Hugging Face downloads with pinned revisions, exact file filters, and a disk reserve. Test cached versus missing bytes before committing to large weights.
Read guide → -
Open WebUI Nginx Proxy: Fix WebSocket and Signup Defaults
Configure Nginx 1.26 in front of self-hosted Open WebUI. Fix HTTP/1.1 WebSocket streaming, bind ports to loopback, and lock open signup defaults locally.
Read guide → -
MiniMind Dataset Preflight: Validate JSONL Before Training
Check MiniMind text and chat datasets locally with a small Python validator. Catch malformed JSONL and missing answers before attempting a training run.
Read guide → -
LiteLLM and Ollama: Set Up a Local-Only Model Gateway
Route a stable model alias to local Ollama with LiteLLM. Check licenses, bind to loopback, disable cloud models, and test failures before connecting your apps.
Read guide → -
Hugging Face Kernels: Check Compatibility Before Installing
Check Hugging Face Kernels licensing, Python and GPU compatibility, then pin a reproducible experiment without promising automatic Ollama or vLLM speedups.
Read guide →