Vibe Coding Discover

RAG

Self-hosted AI gateway for private RAG, natural-language data access, and tool-calling agents.

★ 35157 forksPythonApache-2.0schmitech

Self-hosted AI backend that connects private files, databases, APIs, and MCP tools to local or hosted models through an OpenAI-compatible API. Includes RAG, model routing, authentication, guardrails, observability, and an admin UI.

Use Cases

Chat with private files and documentsAsk natural-language questions across SQL and NoSQL databasesQuery Elasticsearch logs to investigate incidentsConnect agents to APIs and MCP toolsDeploy a governed AI backend in on-premises or air-gapped environmentsBuild voice-enabled assistants over private data

Built With

Language
Python
Frameworks
Ollama · llama.cpp · vLLM · MCP

Tags

self-hosted · RAG · AI gateway · private data · tool calling · MCP · multimodal · OpenAI-compatible API · data adapters · guardrails · observability · voice assistants

orbit — Vibe Coding Discover