AI Potluck
Contribute
Back to Gap Map Product / UX / Orchestration & agents

OpenRAG

Linagora
open source / Overall score: 2.4

Linagora's modular retrieval-augmented generation framework, packaged as a self-hostable application stack rather than a bare library. It ingests PDFs, documents, audio and images with AI captioning, organizes knowledge into partitions, and runs hybrid semantic and keyword search with multilingual reranking. A bundled chat interface, an admin UI and an OpenAI-compatible REST API sit in front, with Ray for distribution across machines and GPUs.

Openness

5 high confidence
5.0
license
AGPL-3.0(OSI)
source
public
self-host
primary(Docker Compose)
core features withheld
no
commercial
none

OpenRAG's entire backend and frontend are published under AGPL-3.0, an OSI-approved license, and that same source is what runs self-hosted via Docker Compose. There is no enterprise tier or vendor lock-in, so the published code is the whole product.

Adoption

1 medium confidence
1.0

OpenRAG is distributed only as a Docker Compose stack, with no first-party PyPI or npm package and no download or user figure, leaving GitHub stars as the only adoption signal available. Because stars alone cannot indicate more than early-stage adoption, the reading here sits at the bottom of that scale.

Capability

3 medium confidence
3.0

Feature-complete, batteries-included general RAG stack with a broad ingestion + retrieval surface and a bundled UI/API. A notch below RAGFlow (capability 4), whose distinctive layout-aware deep document understanding and larger, more mature community set the ceiling for this category.

Verified 2026-09-27