AI Potluck
Product / UX / Orchestration & agents

OpenRAG

Linagora

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.

There is no first-party package on PyPI or npm; Docker Compose is the distribution channel. Verified 2026-08-13 via the linagora/openrag repository.

Openness

5 high confidence
5.0
license
AGPL-3.0(OSI)
source
public
self-host
primary(Docker Compose)
core-gated
ungated
commercial
none

Fully open AGPL-3.0 RAG application stack — the published source is the whole product, self-hosted via Docker Compose, with no feature-gated enterprise tier and no vendor lock-in. AGPL is OSI-approved and sits beside Apache on the software ladder, so osi + public + ungated lands at 5.

  • https://github.com/linagora/openrag recorded 2026-08-13

    AGPL-3.0 license; full source for backend (Python) + frontend (TS/JS); self-hostable via Docker Compose; admin UI, chat UI, and OpenAI-compatible REST API bundled; no paid/enterprise tier

Adoption

1 medium confidence
1.0

238 stars across the one declared repo, with 55 forks, which bands at <1K stars, level 1 on the stars scale - early-stage. No download metric is available, since OpenRAG is distributed as Docker with no first-party PyPI or npm package, so stars are the only signal, and a star-based reading is capped at level 3 in any case.

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.

  • https://github.com/linagora/openrag recorded 2026-08-13

    multimodal ingestion, hybrid search with multilingual reranking, bundled chat and admin UI, OpenAI-compatible API, Ray distribution and GPU acceleration; no benchmark figure

Verified 2026-08-13