KYBERNESIS
HOW_IT_WORKS
// HOW_IT_WORKS

The architecture behind your second brain

Kybernesis extracts facts, detects contradictions, builds entity profiles, and retrieves with precision—all while you sleep.

UploadProcessStoreExtract FactsDetect ContradictionsBuild ProfilesRetrieveAI Agents

The Big Picture

Imagine having a brilliant assistant who reads everything you give them, extracts the key facts, builds profiles of every person and project, detects when information contradicts what it already knows, and can instantly recall exactly what you need—with precision, not noise.

That's Kybernesis. Not a document store—a knowledge engine.

// THE_JOURNEY

From upload to intelligence

Here's how Kybernesis transforms your raw documents into structured, searchable knowledge.

01
UPLOAD

Bring in your knowledge

Drop PDFs, docs, spreadsheets, or paste text directly. Connect Google Drive or Notion for automatic syncing. We handle OCR for scanned documents.

02
PROCESS

Smart extraction

Content is chunked intelligently (~500 words each), keeping ideas together at natural boundaries. Each chunk is embedded into 256-dimensional vectors to capture semantic meaning.

03
STORE

Four-layer storage

Memories live across vector store (256d semantic embeddings), structured database (metadata & relationships), fact store (atomic entity-attribute-value triples), and entity profiles (auto-built from aggregated facts).

// SLEEP_AGENT

The 8-step intelligence pipeline

Every hour, while you're working (or actually sleeping), our AI agent runs a pipeline that transforms raw documents into structured knowledge.

PIPELINE_FLOW:
collecttagextractcontradictprofileslinktiersummarize
LLM_TAGGING

AI extracts semantic tags—entities, topics, and themes—not just keywords. A document about revenue projections gets tagged finance, Q4, revenue, strategic-planning.

FACT_EXTRACTION

AI reads each memory and extracts atomic facts: "Sarah's role is engineering lead", "Project Alpha launches April 15". Each fact is stored with entity, attribute, value, and confidence.

CONTRADICTION_DETECTION

When new facts conflict with existing ones, the system detects contradictions and automatically supersedes outdated information. Your knowledge stays current without losing history.

PROFILE_BUILDING

Aggregates facts into living profiles for people, projects, organizations, and topics. Ask "What do I know about Sarah?" and the system has a ready profile with static facts, dynamic context, and related entities.

RELATIONSHIP_LINKING

Memories get connected with typed edges: related, updates, extends, contradicts. Your project proposal automatically links to research notes, meeting summaries, and budget documents.

PRIORITY_TIERING

Recent, frequently-accessed, highly-connected memories stay in the hot tier. Older, isolated memories move to warm then archive. Nothing is deleted—just organized by relevance.

// KNOWLEDGE_ENGINE

Beyond document search

Most memory systems store documents and search them. Kybernesis understands what your documents mean and tracks how knowledge evolves over time.

knowledge://fact-extraction
LIVE
// Extracted facts from memory:
entity: "Sarah" attr: "role" value: "engineering lead" conf: 0.92
entity: "Project Alpha" attr: "launch_date" value: "2026-04-15" conf: 0.88
entity: "User" attr: "preference" value: "async communication" conf: 0.85
// Contradiction detected:
Sarah → role → "senior engineer"
Sarah → role → "engineering lead" LATEST
// Entity profile built:
PROFILE: Sarah [person]
role: engineering lead (conf: 0.92)
team: Platform (conf: 0.88)
current: Project Alpha migration (dynamic)
related: [Alex, Project Alpha, Platform Team]
TEMPORAL_GROUNDING

Relative dates like "next Thursday" or "last month" are resolved to absolute dates. Facts referencing past events are automatically marked as expired, so retrieval prioritizes current information. "The meeting tomorrow" from three weeks ago won't pollute today's results.

VERSIONED_KNOWLEDGE

Every fact version is preserved with timestamps and supersession chains. When information changes, the old version is deprioritized—not deleted. You can always trace how knowledge evolved: who held what role, when plans changed, and what the latest truth is.

// RETRIEVAL

3-way hybrid retrieval

Three retrieval strategies work together to find the most relevant results with minimal noise.

55%
Vector Search

Semantic similarity using 256d embeddings. Finds documents about the same concepts, even with different words.

25%
Metadata Scoring

Tag overlap, recency, access patterns, and tier priority. Structure meets meaning.

20%
Keyword Scoring

Direct text matching for names, dates, and specific terms that embeddings can miss.

PRECISION_FEATURES:

Chunk Limiting

Returns only the top 2-3 most relevant chunks per memory, not entire documents. Less noise, more signal.

Relevance Floor

Results below a minimum relevance threshold are filtered out. No more padding results with irrelevant matches.

Fact-Aware Scoring

Memories with current (non-superseded) facts matching your query entities get boosted. Outdated facts get deprioritized.

Profile Injection

When your query mentions a known entity, the system includes their profile alongside search results—giving agents instant structured context.

// AI_AGENTS

Profile-powered AI agents

Create AI agents that use your memories, facts, and entity profiles as their knowledge base. They don't just search—they know.

agent://samantha
LIVE_CONVERSATION
YOU:What's Sarah's current role and what is she working on?
SAM:Sarah is the engineering lead on the Platform team. She was promoted from senior engineer last quarter. She's currently leading the Project Alpha migration, which is scheduled to launch April 15th. She also mentioned preferring async communication for status updates.
[PROFILE: Sarah] • [FACTS_MATCHED: 4] • [CONTRADICTION_RESOLVED: role updated] • [MEMORIES: 3]
ENTITY_PROFILES

Agents access auto-built profiles for instant context. Mention a person, project, or topic and the agent already knows the key facts.

SELF_MODIFYING

Agents evolve through conversation. Say 'be more casual' and their persona updates instantly. Context persists across sessions.

ARCHIVAL_MEMORY

Agents query your workspace memories via 3-way hybrid search with fact-aware scoring. Instant access to all your knowledge.

TOPOLOGY_VIEW

See your knowledge as a living graph

The Topology visualizes memories as nodes and relationships as edges. Watch clusters form around themes, discover unexpected connections, and see how entity profiles link your knowledge together.

nodes = memories|edges = relationships|clusters = themes
TOPOLOGY

Privacy & Security

Your memories are yours.

All data encrypted in transit and at rest
Multi-tenant isolation—your data is completely separate
OAuth connectors only access files you authorize
API keys let you control programmatic access
// WHY_KYBERNESIS

What makes this different

It extracts knowledge, not just documents

Most memory systems store and search raw text. Kybernesis extracts atomic facts, builds entity profiles, and creates a structured knowledge graph from your unstructured data.

It knows what's current

Contradiction detection and temporal grounding ensure you always get the latest information. When facts change, old versions are superseded—not deleted, just deprioritized.

It retrieves with precision

3-way hybrid scoring, chunk limiting, relevance floors, and fact-aware ranking mean you get the most relevant excerpts—not 40 chunks of loosely related text.

It gives agents real context

Entity profiles and structured facts mean your AI agents don't just search—they know. Ask about a person and the agent has their role, projects, and relationships at hand.

// GET_STARTED

Your knowledge engine is ready

Upload a few documents. Watch the Sleep Agent extract facts, build profiles, and organize everything. Search using natural language. Create an agent that actually knows your context.

1. Upload
2. Watch it learn
3. Search & discover
4. Create agents
Free tier • No credit card required