AI Potluck
Product / UX / Orchestration & agents

SyftHub

OpenMined

An open, privacy-preserving federated RAG framework from OpenMined. Instead of centralizing documents, a query is broadcast across a network of peers; each peer searches its own private index and returns only the most relevant snippets, which are aggregated, ranked, and synthesized by an LLM into a grounded answer. The SyftHub SDK loads data sources from the network, selects an LLM, and runs federated RAG pipelines. Built on OpenMined's Syft privacy stack.

SyftHub federated RAG SDK, Apache-2.0, from OpenMined; ~2 GitHub stars (July 2026), created Aug 2025. Early-stage; part of OpenMined's federated-RAG work (alongside local-rag / local-rag-router) and built on the Syft privacy stack (PySyft is tracked separately). Verified live July 2026.

Openness

5 high confidence
5.0
license
Apache-2.0(OSI)
source
public(github.com/OpenMined/syft-hub-sdk)
self-host
yes
service
none

Fully open source: Apache-2.0 SDK, self-hostable, no proprietary tier. Built on OpenMined's open Syft privacy stack.

Adoption

1 low confidence
1.0

~2 GitHub stars (July 2026), created Aug 2025 — pre-adoption. Part of OpenMined's federated-RAG effort (also local-rag, local-rag-router). Included as an emerging entry, not on adoption merit.

Capability

2 low confidence
2.0

Implements a full federated RAG pipeline — distributed private indexing, federated query broadcast, local top-k retrieval, global aggregation/ranking, and LLM synthesis. A distinctive privacy-preserving approach (nothing else on the map does federated RAG), but early-stage and narrow.

Unchanged since 2026-07-01 (last edited, not re-checked)