n8n
n8n is workflow automation you run on your own infrastructure. It connects the applications a business already uses through a visual editor, with hundreds of prebuilt nodes, a code step for anything bespoke, and native support for calling language models mid-flow. Think of it as a self-hosted alternative to Zapier or Make that you own outright, including every piece of data passing through it.
View the repo · n8n-io/n8n ↗Teams automating intake, routing, reporting and reconciliation across their existing stack, especially where the data is too sensitive to route through a third-party automation cloud. It suits operations and finance teams with a technical person on hand, because self-hosting means someone owns upgrades, backups and credentials. If nobody in the business can run a Docker container, a hosted automation tool will serve you better until that changes.
Install itnpx n8n
# or with Docker:
docker run -it --rm -p 5678:5678 docker.n8n.io/n8nio/n8nThe default SQLite database is fine for evaluation and struggles under real load, so move to Postgres before you depend on it. Every connected system's API key ends up stored inside n8n, which makes credential handling and backups worth deliberate care. The licence is fair-code rather than classic open source: internal business use is fine, while reselling n8n itself as a hosted service is restricted. Always put a human approval step before any node that sends money, emails or contracts.
Where Blash AI comes inn8n is usually the deterministic backbone of a Blash build: it moves the data, and the model steps we add supply the judgement. We design the workflows, wire them to your CRM and finance system, route model calls through a gateway such as LiteLLM from this library, and add the logging, retries and audit trail that separate a demo from a system your team relies on every day.
When you want this running on your real stack, that is the engagement
Book an AI audit →Ollama →
Ollama runs open-weight language models on your own machine or server. One command downloads a model and serves it behind a local API that most existing AI tooling can talk to, so an application built against a hosted provider can point at your own hardware instead. Sensitive data stays inside your network, there are no per-token fees, and it keeps working with no internet connection at all.
LiteLLM →
LiteLLM is a gateway that lets you call models from Anthropic, OpenAI, Google and many other providers through one consistent API. It runs as a Python library inside your code or as a standalone proxy server in front of your whole stack, with cost tracking, per-key budgets, rate limits and automatic fallbacks for when a provider has a bad day.
Chroma →
Chroma is an open-source vector database, the store behind retrieval-augmented generation. You embed your documents, Chroma indexes the embeddings, and at question time it returns the passages closest in meaning to the query so a model can answer from your own content with citations. It runs embedded inside a Python process for prototypes or as a standalone server for shared use.