Back to directory

Vyral

An open-source, local-first contract layer and runtime for applications that need canonical data storage, retrieval and RAG, and durable execution, without locking application code to one cloud provider.

Vyral

Vyral keeps these capabilities behind stable, application-owned contracts instead of vendor SDKs, so an application can start on a laptop with one command and later move individual capabilities to SQLite, Postgres with pgvector, Azure, AWS, Google Cloud, Cloudflare, Temporal and other providers without changing application code.

A local quickstart runs lexical retrieval with citations, admits durable work, reopens the runtime, and completes a preserved run, with no package installation, cloud account or model download required; an editable application is then created with vyral init.

Language-neutral conformance fixtures and a versioned qualification matrix make what each adapter actually supports explicit rather than assumed, and clients exist for Python, JavaScript and Go.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.