This hub indexes the long-term technology roadmap that turns Wikantik from "a wiki with excellent agent surfaces" into a credible competitor in the RAG-as-a-service market. It was produced from a 2026-07-10 market gap analysis comparing Wikantik against commercial and open-source offerings: Glean, Onyx, Amazon Bedrock Knowledge Bases, Azure AI Search, Vectara, Ragie, LlamaCloud/LlamaIndex, Pinecone, and Unstructured.
Each linked page is a one-page capability brief designed to bootstrap a deep-dive investigation by an agent or a team: gap statement, market grounding with sources, current Wikantik state with code and design-doc entry points, a proposed direction, Phase-1 acceptance criteria with a first-session scope, a verify-before-designing claims list, non-goals, and tagged open questions. The expected next step for any brief is the project's standard process: brainstorm → design doc → phased implementation.
Wikantik should not chase Glean's 100-plus-connector arms race or Bedrock's managed-everything on their terms. The defensible position, supported by the market research, is the self-hosted, agent-native, curated knowledge base: content that is verifiable (version-pinned citations, span-hashed staleness tracking, page verification workflow), machine-legible (RDF/SPARQL ontology, frontmatter, structural spine), and served through the protocol agents actually use (MCP). Practitioner reports describe a migration away from server-side prompt-stuffing pipelines toward MCP-mediated retrieval where the agent drives its own search — Wikantik is already built for that world.
Three existing moats to defend and market, not rebuild:
The Tier-1 gaps below are what make the RAG-as-a-service claim credible; the rest are parity checkboxes buyers will checklist.
RoadmapTargetArchitecture is the architectural spine binding the briefs together. It defines the end state as an incremental evolution of the current modular monolith — new satellite modules (wikantik-connectors, wikantik-authz-sync), two retrieval pipeline seams (QueryPlanner pre-retrieval, RerankChain post-fusion), authorization pushdown at the single existing enforcement chokepoint, PostgreSQL-first for all new state, and the deployment boundary as the tenant boundary. It also fixes the eight invariants (no synthesis, fail-closed retrieval, async indexing, one authz chokepoint, PostgreSQL-first, no wikantik-main growth, measure-first, complete Apache 2.0 core) that any capability design must respect, and a capability-to-seam map showing where each brief's implementation attaches. Read it before starting a design doc for any brief.
Every open question in the capability briefs carries one of three tags. Agents executing a brief MUST respect them:
[OWNER] — business, pricing, licensing, legal or compliance claims, security postures (permission-staleness windows, data retention), product shape, spend, or additions to the public API surface. The agent's job is to prepare options with a recommendation and stop; the owner decides. Never resolved autonomously, however confident the analysis.[AGENT] — resolvable by reading code, running a spike, or design judgment within the RoadmapTargetArchitecture invariants. Decide it, document the decision and rationale in the design doc, and proceed.[MEASURE] — resolved by running the eval harness or a measurement script. The number decides; neither the agent nor the owner argues with it.Two standing owner gates beyond the tags: the multi-tenancy posture ADR (RoadmapMultiTenancyPosture) may be drafted by an agent but is only ratified by the owner; and RoadmapPackagingAndPricing is owner-gated end-to-end — agents prepare decision inputs there, never binding designs.
| Tier | Capability | Horizon | Why this tier |
|---|---|---|---|
| 1 | RoadmapConnectorFramework | Now (0–3 mo design, first connectors) | Widest gap; every source names connector breadth the primary differentiator |
| 1 | RoadmapExternalAclInheritance | Next (3–9 mo) | Permission-aware retrieval from connected sources is the enterprise gate; co-evolves with connectors |
| 1 | RoadmapMultiTenancyPosture | Later (9–18 mo), decision now | Defines the product shape: silo-per-tenant fleet vs shared-store multi-tenancy |
| 2 | RoadmapComposableReranking | Now (cheap, measurable) | Deterministic MMR/metadata-boost stages are low-cost parity with Vectara chain reranking |
| 2 | RoadmapAgenticRetrieval | Next | Query decomposition + sufficiency evaluation is now table stakes in Bedrock and Azure demos |
| 2 | RoadmapMultimodalIngestion | Next | Diagrams and scanned documents are invisible to the current text-only pipeline |
| 2 | RoadmapRetrievalEvaluationObservability | Now (phase 1) | Internal harness exists; productizing it is differentiation, not new science |
| 3 | RoadmapCompliancePosture | Next (whitepaper) → Later (SOC 2) | Procurement table stakes for the commercial path |
| 3 | RoadmapPackagingAndPricing | Later | Open-core packaging follows, not precedes, the Tier-1 capabilities; owner-gated end-to-end |
| 3 | RoadmapClientSdkDeveloperExperience | Now (quick win) | The LangChain/LlamaIndex retriever adapter is the genuine quick win; the full DX program is multi-session |
Execution ordering constraints beyond the tier table — start nothing whose upstream box is unresolved:
ConnectorFramework (schema carries source ACL refs from v1)
│
▼
ExternalAclInheritance (enforcement over those refs)
│
▼
CompliancePosture (retrieval audit + GDPR delete propagation ride connector tombstones)
MultiTenancyPosture: cost-floor measurement [MEASURE] ──▶ PackagingAndPricing (unit economics)
MultiTenancyPosture: posture ADR [OWNER] ──▶ tenant-in-a-box + fleet control plane work
RetrievalEvaluationObservability phase 1 (scheduled harness) ──gates──▶
ComposableReranking, AgenticRetrieval, MultimodalIngestion (each accepted only on harness evidence)
ComposableReranking (RerankChain SPI) ──▶ AgenticRetrieval (decomposed results feed the chain)
TargetArchitecture API-stability contract ──▶ ClientSdkDeveloperExperience (SDK freezes the wire format)
MultimodalIngestion — independent once its diagram eval-set extension exists
Market claims in these briefs come from a 2026-07-10 research sweep over 18 sources (vendor documentation from Glean, Onyx, AWS, Azure, Vectara; multi-tenant RAG reference architectures; evaluation-tooling surveys). Claims were extracted from primary sources but not independently cross-verified — treat specific counts and prices as approximate. Each brief now carries a "Verify before designing on these" list isolating the claims whose falsity would change the design; verify those, and only those, before the design doc.