91.32%on EnterpriseRAG-Bench
EnterpriseRAG-Bench asks enterprise questions over a large company corpus and judges each answer on whether it is correct and complete.
How it was measured/Louvain Engine · open source · Apache-2.0
Hybrid search over your company’s documents for agents and RAG, with a permission check in every query, from one command.
91.32%on EnterpriseRAG-Bench
EnterpriseRAG-Bench asks enterprise questions over a large company corpus and judges each answer on whether it is correct and complete.
How it was measured01Why the engine
Keywords and meaning search together, so the right document comes first however the question is worded. Add a reranker in one line when you want more.
Every query passes a permission check first. Add readers and grant each the collections it may read, in config; Louvain syncs real permissions from your tools.
MCP tools for your agents, plugins as plain functions, and Postgres underneath. Open source, under Apache-2.0.
02How it works
Folders, records or HTTP
Keywords and meaning
The fence first, every query
The right document, with its source
03Quickstart
git clone https://github.com/louvain-ai/louvain-engine && cd louvain-engine
./engine up
./engine ingest folder --folder examples/sample-corpus
./engine search "When does the Harbour Street lease renew?"
04Open source
The engine is open source under Apache-2.0. It runs on your machine, and nothing leaves it unless you choose a hosted reranker or model.
Louvain Engine, run for your company: a brain in seconds, configured lane by lane, with permissions on a dial.