Tools worth your weekend
The open-source AI tools we actually build on, across workflow automation, local AI, retrieval, document AI and analytics. Each one shows what it does, who it is for, and how to run it. Try one yourself. When you want it wired into your real stack, that is the engagement.
Categories: Workflow automation · Local AI · RAG and retrieval · Document AI · Analytics and BI · Finance and ops
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.
Local AIOllama →
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.
Local AILiteLLM →
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.
RAG and retrievalChroma →
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.
RAG and retrievalLangChain →
LangChain is a framework for building applications on top of language models. It supplies the plumbing: document loaders, text splitters, retrieval wrappers, tool and agent abstractions, and integrations with most model providers and vector stores, including Chroma from this library. For teams that would otherwise hand-roll the same glue code, it offers ready-made building blocks with a very large ecosystem behind them.
Document AIUnstructured →
Unstructured is a Python library that turns messy real-world files into clean, structured elements an AI workflow can use. It ingests PDFs, Word documents, PowerPoint, emails, HTML and scanned images, detects titles, paragraphs, lists and tables, and emits typed elements with metadata ready for chunking and embedding. It exists because business documents rarely arrive as tidy text.
Document AIMarker →
Marker converts PDFs into clean Markdown, handling the tables, equations, figures and multi-column layouts that make general-purpose parsers give up. It uses a pipeline of deep-learning models for layout detection and text recognition, and it is built for exactly the dense reports, filings and technical documents that carry most of the value in a document workflow.
RAG and retrievalAnythingLLM →
AnythingLLM is a self-hosted application for chatting with your documents, complete out of the box: a web interface, workspaces that scope which documents a conversation can see, user management, and connectors for a wide choice of model providers and vector stores. It is the quickest route in this library to putting a working internal knowledge assistant in front of real users.
Analytics and BIMetabase →
Metabase is open-source business intelligence. It connects to the databases you already run, lets non-technical staff ask questions through a point-and-click editor while analysts drop to SQL when they need to, and turns the results into dashboards, scheduled email reports and alerts. One Docker container gets you a working instance in minutes.
Finance and opsERPNext →
ERPNext is a full open-source ERP built on the Frappe framework, covering accounting, inventory, manufacturing, CRM, projects and HR in one integrated system. It is a serious alternative to the costly mid-market suites, with no licence fees per user and complete access to your own data and code, and it deploys cleanly with Docker.
Workflow automationCal.com →
Open-source scheduling you can self-host, embed in your own product and connect to your own calendar stack. The self-hostable codebase now lives under the Cal.diy name, described by its maintainers as scheduling infrastructure for absolutely everyone, while Cal.com continues as the hosted service. You get booking pages, round-robin and team scheduling, and an API for driving it all programmatically, with booking data kept inside your own systems.
Finance and opsDocumenso →
Documenso is open-source document signing, a self-hosted alternative to DocuSign for contracts, engagement letters and approvals. Upload a PDF, place signature and text fields, send it for signing and track completion, either through the web interface or entirely through its API, with the signed documents and their audit evidence staying inside your own infrastructure.
Document AIFirecrawl →
Firecrawl crawls and scrapes websites into clean Markdown and structured data built for language models. It renders the JavaScript-heavy pages that simple HTTP scrapers miss, follows a site to a set depth, and returns content ready for indexing or extraction, through either a hosted API or a self-hosted deployment of the open-source service.
Analytics and BIPlausible Analytics →
Plausible Analytics is lightweight, privacy-friendly web analytics you can self-host. It measures traffic without cookies or personal-data collection, which keeps most visitors outside consent-banner territory, and presents everything on a single fast dashboard. The script it adds to your pages is a fraction of the size of the mainstream alternative, and the Community Edition runs on your own server.