Ollama
Local runtime that downloads, quantises and runs open-weight language models, exposing them over its own HTTP API and an OpenAI-compatible endpoint. Also serves embedding models.
A complete local AI infrastructure that provides everything needed to build and deploy intelligent agents without relying on cloud services. This bento box creates a self-contained ecosystem where Ollama serves local language models, n8n orchestrates complex multi-step workflows, Supabase provides a robust database foundation with built-in authentication and vector storage, Open WebUI offers an intuitive chat interface for interacting with your agents, and Caddy handles all the networking and SSL termination automatically. Together, these services solve the fundamental challenge of creating production-ready AI agents that can operate entirely within your own infrastructure while maintaining professional-grade reliability and security. The combination is specifically designed for teams and individuals who want to experiment with agent architectures without the complexity of enterprise-scale deployments.
Local runtime that downloads, quantises and runs open-weight language models, exposing them over its own HTTP API and an OpenAI-compatible endpoint. Also serves embedding models.
Workflow automation platform with 400+ service integrations, extensible in JavaScript. Runs event-driven and scheduled flows across APIs, databases and model endpoints.
Backend platform assembled around PostgreSQL, adding generated REST and GraphQL APIs, authentication, authorisation through row-level security, file storage and realtime change streams.
Self-hosted chat interface for local and remote language models, adding document retrieval, model switching, per-user workspaces, tool calling and an extensible pipeline layer.
Web server and reverse proxy that obtains and renews TLS certificates automatically, supports HTTP/3, and is configured either by a short text file or entirely over an API.