Long-running IPs have a memory problem
When a sequel arrives years later, audiences struggle to recall what happened. The barrier to re-entry hurts engagement and box-office returns.
The narrative knowledge graph for the AI era
Knibu turns stories into structured, queryable knowledge.
We transform films, TV series, manga, and novels into a temporally-aware narrative knowledge graph — so fans can revisit any story with confidence, creators can design with structure, and AI agents can retrieve reliable narrative context.
Why now
Why narrative needs structure
Creators work in unstructured prose
Maintaining continuity, character arcs, and timeline logic across a large story is hard — and getting harder as stories grow.
AI agents lack reliable narrative grounding
General models hallucinate plot details; web search returns noisy, inconsistent results. There's no trustworthy, structured source of narrative truth.
The product
One knowledge graph, three ways to use it
The same temporally-aware engine, surfaced for three audiences.
For fans
Knibu App
Catch up on the stories you love, before the next chapter drops.
- Ask any question about a story in natural language and get reliable, source-grounded answers with visual explanations.
- Browse events, characters, and relationships as they change across the story's timeline.
- Generate shareable visual summaries to discuss key moments with your community.
For creators
Knibu Studio
Build your story as a structure, not just a document.
- Design characters, events, and timelines on a visual canvas with AI assistance.
- Reference and analyze how existing works handle similar arcs, beats, and structures.
- Collaborate with co-writers and export structured work to manuscript form.
For developers & AI agents
Knibu API / MCP
Reliable, time-aware narrative context for AI agents.
- Query structured narrative facts — events, character states, relationships, timeline-anchored details — via a simple API.
- Connect through the Model Context Protocol (MCP) so any AI agent can access narrative knowledge as a tool.
- Built for grounding: structured graph retrieval for discrete facts, semantic search for abstract concepts.
How it works
How Knibu works
01 / Ingest
From story to data
We process story content into structured narrative data: events, entities, relationships, and their changes over time.
02 / Structure
Into a temporal graph
Information is organized into a temporally-aware knowledge graph that preserves internal logic and consistency.
03 / Access
Out as answers
Users query in natural language; the system retrieves the right facts and presents them through clear, purpose-built views — or serves them to AI agents via API.
The complexity lives in the graph; the experience stays simple.
Where we are
An honest look at our progress
Narrative ingestion pipeline (video + text)
Operational
Knowledge graph database & schema
Operational
20+ major IPs already processed
Done
Natural-language query & visual presentation
In development
Fan app (iOS)
In development
Developer API & MCP server
In development
Creator Studio
Planned
Operational
In development
Planned
Built for scale
Knibu runs an AI-intensive, cloud-native stack. Our ingestion pipeline processes large volumes of multimodal content using large language models, and our temporally-aware knowledge graph is hosted on managed cloud infrastructure. As we scale ingestion across thousands of works and serve real-time queries to fans, creators, and AI agents, cloud compute and managed AI services are central to our architecture.
20+
Major narrative IPs processed
Multimodal
Video + text ingestion via LLMs
Real-time
Queries for fans, creators & agents
Team
Who's building Knibu
Zhengxiang Tang
Founder & CEO
A one-person company building the full Knibu stack, with 95% of the code written through AI-assisted development. Background in engineering, coding, and product management; graduate of the University of Wisconsin–Madison; four years of experience as a founder.
Be part of the early Knibu community.
We're opening early access to fans, creators, and developers. Tell us how you'd use Knibu.
We'll reply from contact@knibu.com