AI agent memory · GraphRAG
Build graph-backed AI applications with a shared knowledge graph for agents and apps — through MCP and APIs, without running complex graph infrastructure.
Knowledge Graph · GraphRAG · MCP · Managed Hosting
Free to start. No credit card required for P2P.
Agents forget between sessions. Retrieval returns disconnected chunks. Operating graph infrastructure steals time from the application you are building.
Keep useful entities, claims, and relationships available across sessions.
Represent how people, events, documents, and decisions relate — not only which text looks similar.
Use a managed option, or run your own peer, without coupling graph truth to one database host.
Give agents memory that survives the session instead of isolating knowledge in chat history.
Store and query entities, claims, and relationships instead of only disconnected chunks.
Expose the same tenant-scoped graph through APIs and MCP.
Preserve graph state and provenance through content-addressed commits.
Traditional RAG is useful for finding related passages. Graph-backed AI adds explicit entities, claims, and relationships so an agent can follow connected context.
Kotobase complements retrieval; it does not claim that every workload should replace vector search.
Applications and agents access the graph within the same tenant identity boundary.
Signed immutable commit CIDs make the selected graph state explicit and reproducible.
Clients can query, cache, compute, and contribute verified CID-addressed results.
Give agents a graph tool surface without building one-off retrieval glue for every application.
https://kotobase.net/mcp
Tools are generated from the same published lexicons used by the application API.
Represent the people, products, organizations, documents, and events your application reasons about.
Keep assertions and their graph context available across sessions and applications.
Use Datalog, SPARQL, or Cypher-style query surfaces for the shape of query you need.
Bind work to content-addressed graph commits instead of an implicit mutable database state.
Kotobase is an option to evaluate when you want a knowledge graph for agents and applications, MCP access, managed hosting, or content-addressed provenance.
| Evaluation factor | Kotobase |
|---|---|
| Start | Free P2P option; no credit card required |
| Agent access | MCP |
| Knowledge graph | Yes |
| Managed option | Yes — Secure Managed |
| Query | Datalog, SPARQL, and Cypher-style |
| Provenance | Content-addressed commit CIDs |
| Self-managed option | Yes — run your own peer |
Use the API or point an MCP-capable agent at https://kotobase.net/mcp.
Write entities, claims, and relationships, then query the same tenant-scoped graph from agents and applications.
ipfs pin remote service add kotobase https://kotobase.net <JWT>
ipfs pin remote add --service=kotobase --name=my-doc <cid>
ipfs pin remote ls --service=kotobaseAuthenticate writes and tenant operations with a gftd-AUTHN JWT (Bearer) or self-signed CACAO. Public exact-CID reads are live at /ipld/:cid; canonical queries select an explicit signed commit CID rather than a mutable database head. Built on kotoba.
Start with P2P for experiments and self-managed projects. Choose Secure Managed when a production team wants Kotobase operated for them. Use Enterprise for regulated and mission-critical workloads.
¥0
Developers, self-hosters, researchers, and peers federating their own kotoba node.
You carry operational risk
Run your own peer, or use the shared endpoint as-is. No operator responsibility.
The operator accepts no responsibility on this plan. The service is provided "as is" and "as available" with no availability commitment, no service credits, no incident-response obligation, no recovery objective, and no support obligation. You run your own peer, or you accept the shared endpoint's best-effort behaviour and design your application to tolerate it.
¥19,800 / month
Teams and production applications that need someone accountable for uptime and data handling.
Gftd Japan K.K. is responsible
Gftd Japan K.K. operates it and is accountable for it. 99.9% SLA with service credits.
Gftd Japan K.K. carries operational responsibility on this plan: it operates, monitors, patches, and recovers the service; it commits to a 99.9% monthly availability SLA backed by service credits; it acknowledges customer-reported incidents within one business day; and it holds itself to the published data-handling and security boundary. Availability is measured by the daily SLO gate, whose receipts are committed to the repository.
Custom contract
Financial, medical, government, and enterprise data teams under audit or regulatory obligation.
Gftd Japan K.K. is responsible under contract
99.999% SLA, SOC 2-class compliance response, dedicated infrastructure. By contract.
Gftd Japan K.K. carries operational responsibility on the terms of a signed enterprise contract, which can exceed the published ones: a 99.999% monthly availability SLA with a service-credit schedule, 24x7 named support with a 15-minute P1 acknowledgement, dedicated tenant and infrastructure, counsel-approved privacy terms where available, data-residency commitments, customer-held key custody, read audit, and agreed retention and deletion policy. These commitments attach to the dedicated deployment the contract provisions; they are not offered on the shared production endpoint.
The binding version of these statements is the Terms of Service (§6 plans, §7 service levels, §8 limitation of liability); the engineering detail is in docs/PLANS.md.
A 26-second monthly error budget, with service credits: below 99.999% → 10% of the monthly fee; below 99.99% → 25% of the monthly fee; below 99.9% → 50% of the monthly fee; below 99.0% → 100% of the monthly fee, plus termination for cause without penalty.
Available only by signed contract on a dedicated deployment that clears the readiness gates in docs/PLANS.md; it is not offered on the shared endpoint.
Available today: Security questionnaire and audit response.
Legal review required: Data Processing Addendum (DPA), Business Associate Agreement (BAA). These are not available for execution until qualified counsel approves them.
In preparation: SOC 2 Type II, ISO/IEC 27001, ISMAP (Japan government cloud registration). No report or certificate has been issued yet.
Data residency (in-jurisdiction cold pins); Read audit (universal read receipts); Customer-held key custody (HYOK/KMS).
Named technical account manager, dedicated escalation channel · 15 minutes for P1, 2 hours for P2 · 24x7
Keep Obsidian as your local-first writing space and Markdown as the source of truth. Sync notes, frontmatter, and [[wikilinks]], then query the vault as a graph.
Pinned commit blocks can be archived as CAR files to an S3-compatible immutable object store. Providers improve availability but do not choose graph truth.
No. Applications and agents can query the same tenant-scoped knowledge graph through APIs and MCP.
Not necessarily. Vector search finds similar content; a knowledge graph preserves explicit entities, claims, and relationships. They can be used together.
Kotobase offers a Cypher-style query surface, but this page does not claim wire compatibility. Validate your schema and queries before migrating.
Yes. The P2P plan has no payment checkout. Secure Managed is a paid self-serve subscription; Enterprise is contract-led.
Start with a connected knowledge graph for agents and applications.