Knowledge RAG — Permission-aware RAG for AI agents
Info Inlet Inc. · Software Development
Certification per Microsoft Marketplace.
Evidence tier Source Confirmed · 8 captures on record
What the publisher says
As described on Microsoft Marketplace.
Knowledge RAG is a transactable API that gives AI agents a permission-aware RAG knowledge base. Ingest your documents into a workspace, then have agents
or against them — with hard per-document access control so an agent only ever retrieves what the calling user is allowed to see.
Show the rest of the publisher’s description (21 more lines)
Built for enterprise AI assistants where leaking the wrong document is a compliance event: customer support copilots, internal-knowledge chat, HR / finance / legal assistants, agentic
workflows over private corpora.
Key features
- Permission-filtered retrieval — every chunk has a ; and intersect against caller server-side.
Disallowed chunks never reach the LLM context.
- Hybrid retrieval — dense vectors (Qdrant) + lexical (Postgres FTS) fused with Reciprocal Rank Fusion; optional graph lane for entity-based queries.
- Cited, grounded answers — refuses outside knowledge; every claim carries a [n] citation back to the source chunk.
- Multi-tenant by workspace — chunks are isolated by your subscription; cross-tenant leakage is structurally impossible.
- Japanese-first text handling — CJK-aware chunking and lexical bigrams, so Japanese RAG works out-of-the-box (most global RAG APIs treat JP as one token per sentence).
- Open MCP client — install the free npm package and any MCP-aware client (Claude Desktop, Cursor, etc.) gets /
/ tools instantly.
How it works
- Subscribe to a plan on Microsoft Marketplace; you receive an API key by email.
- Call with workspace id + text → we chunk, embed, and index into both lanes.
- Call for top-K chunks, or for a grounded answer with citations.
- Caller's array is intersected with each chunk's on every call.
Plans
- Starter — $9 / month. 200 queries included. $0.05 per overage query. Ingest is free.
- Pro — $39 / month. 2,000 queries included. $0.03 per overage query.
Architecture — hosted on dedicated EU bare-metal (Hetzner, not in Azure); TLS 1.2+ via Cloudflare; API keys SHA-256 hashed at rest; no document content sent to or stored in Azure.
Interactive Swagger docs at api-rag.knowlez.com/docs; OpenAPI spec at .
Preview
1 image
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment · as of 2026-08-29
Plans and pricing as listed
3 listedSources
Publisher resources
1 linkLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.