Knowledge Operating System

From data to knowledge. From knowledge to action.

The knowledge operating system for the enterprise.

Every organization drowns in data and starves for knowledge. Syrtis captures it from any source, keeps it live and sovereign, and delivers it on demand — every answer traceable back to its source.

31
node types
4
native memories · sql · vector · graph · doc
100%
local or hosted · per node
2024
continuous R&D · one held direction

The problem

AI that gets it wrong doesn't have a model problem. It has a foundation problem.

Every agent, copilot and automation you stack on top is only as good as the knowledge beneath it. Give a brilliant model stale, contradictory or ungoverned knowledge and you don't get “I don't know” — you get a confident, plausible, wrong answer.

Hallucinations are almost always knowledge-layer failures: the right source was missing, out of date, or never trustworthy. No amount of prompt-engineering fixes a weak foundation.

If the knowledge layer isn't excellent and actively maintained, everything built on top inherits its errors.

The substrate — the context engine

The right context, assembled on demand.

Capture, index across multiple memories, then retrieve exactly what's needed — from each one — to build an agent's context. Live.

Context Engine — knowledge substrate
CaptureIndexRetrieveAssemble
Sources
Indexing
Memories
DocumentsPDF · DOCX · MD
SQL databasePostgres · MySQL
API / WebhookHTTP · n8n
Conversationlive session
Chunk · Embed · Relate
Vectorrel + embeddings
12,840 vectors
Graphontology
3,120 relations
Documentsemi-structured
9,450 documents
Filesobjects
2,210 files
?“ What is our refund policy? ”
Assembled context0 / excerpts
Agent · sourced answer
grounded · cited · traceable
  1. 1Capture
  2. 2Index
  3. 3Retrieve
  4. 4Assemble
Sources
DocumentsPDF · DOCX · MD
SQL databasePostgres · MySQL
API / WebhookHTTP · n8n
Conversationlive session
Chunk · Embed · Relate
Memories
Vectorrel + embeddings
12,840 vectors
Graphontology
3,120 relations
Documentsemi-structured
9,450 documents
Filesobjects
2,210 files
Assembled context
VECvector · sim 0.86 · chunk #1284
GRAPHgraph · 3 neighbors · ontology
DOCdocument · manual v4 · §2.1
Agent · sourced answer
grounded · cited · traceable
CaptureDocuments, SQL and graph databases, APIs, conversations — everything enters through the indexer.
IndexChunked, vectorized, related — routed to the memory that fits it.
RetrieveOne query draws from several memories: nearby vectors, graph neighbors, exact rows.
AssembleThe excerpts form the agent's exact context — every answer traceable to its source.

Retrieval — multi-RAG & consensus

Many methods. One consensus.

Vector, graph, full-text, SQL: every memory is queried in parallel, then the results are crossed. What several methods confirm rises; the noise drops. Every dial is in your hands — or automated for performance.

queryTermination clauses for critical suppliers
auto
vector · precision ↔ recall
Assembled contextHIGH
5 retained4 consensus4/4 methods
  • Amendment 2024-117 · early termination (90-day notice)contract · active
    ×4 consensus
  • Procurement policy · supplier exit conditionsdoc · v4
    ×3 consensus
  • Email thread · notice period with ACME Corpmessage · 03-2024
    ×2 consensus
  • Critical suppliers register · tier 1table · sql
    ×2 consensus
  • Internal newsletter · new suppliers Q3doc · comms
    1 method

Consensus across methods is what makes precision. The threshold tunes vector recall — raise it to cut noise, lower it to widen.

The KOS, put to work

Agents that store and consume knowledge.

The substrate isn't just storage. Above it, agents read the context they need and write fresh knowledge back — for concrete goals, all backed by the same foundation.

Agents backed by the shared substrate
↑ consume · read↓ store · write
Knowledge transfer
Pulls expertise out of people's heads, files it as a reusable asset.
write ++read
Onboarding
Turns internal knowledge into adaptive, always-current guidance.
read ++write
Adaptive training
Assesses, guides, teaches one concept at a time — where Syrtis began.
readwrite
Fact-checking
Cross-checks a claim against authoritative knowledge, flags the gaps.
readflag
Customer support
Answers from your sources — never a generic hallucination.
read ++write
Knowledge OS — shared substrateVECGRAPHDOCSQLprovenance · versions
Knowledge transfer
Pulls expertise out of people's heads, files it as a reusable asset.
write ++read
Onboarding
Turns internal knowledge into adaptive, always-current guidance.
read ++write
Adaptive training
Assesses, guides, teaches one concept at a time — where Syrtis began.
readwrite
Fact-checking
Cross-checks a claim against authoritative knowledge, flags the gaps.
readflag
Customer support
Answers from your sources — never a generic hallucination.
read ++write
Knowledge OS — shared substrateVEC · GRAPH · DOC · SQL · provenance · versions
↑ consume — the agent reads the context assembled from the KOS↓ store — the agent writes back fresh knowledge, versioned and traced

The control surface

No decision behind a curtain.

You stay in control of every AI decision — which model, which knowledge, which database, how it's retrieved, monitored, versioned. Pick a node's model and watch sovereignty react.

model · per node
storage · substrate
Risk levelMEDIUM
ProcessingAnthropic · US cloud
StorageSyrtis · on-prem
GDPRNon-EU transfers
EU AI ActConditional
SovereigntyVendor dependency
SecurityCloud exposure

Knowledge stays in the sovereign substrate; only the processing location changes.

Sovereignty by selection

Point sensitive steps at a local model — data never leaves your perimeter — and reserve hosted frontier models for the steps that deserve them, in the same flow.

“Lovable for pipelines”

Describe the flow in plain language; Syrtis turns it into a buildable Scenario blueprint, constrained to the real vocabulary and the 31 real nodes. An AI service in hours, not months.

Iterate without risk

Every slot and the API are versioned; the Trace node consolidates a run's full history. Quality, drift, cost, CO₂ — observable, audit-ready.

How it's built

A micro-services platform, one control plane.

Three applications, a message bus, a multi-store data layer, and a deterministic DAG executor. One vocabulary, from the UI down to the tables.

Interface

Manager

The graph-first scenario editor, the test chat/console, the request waterfalls and the supervision dashboards.

Source of truth

API

The single source of truth. Persists every entity, enforces access rights, records requests and bridges to Core over the bus.

Execution engine

Core

The brain. Consumes jobs, runs the node DAG, drives the LLM interactions and rendering — and emits the Messages.

The library — 31 atomic nodes

AI / LLM06
  • Converse
  • Reason
  • Extract
  • See
  • Listen
  • Imagine
Knowledge05
  • Ingest
  • Chunk
  • Embed
  • Retrieve
  • Ground
Messages04
  • Emit
  • Seal
  • Stream
  • Archive
Flow06
  • Branch
  • Route
  • Loop
  • Compose
  • Pass
  • Wait
Integration07
  • Code
  • Shell
  • Remote
  • Fetch
  • n8n
  • Query
  • Graph
Session03
  • Pulse
  • Scan
  • Trace

Why Syrtis

AI-native by design. Not a black box, not a repurposed tool.

The alternatives are either black boxes you can't open, or tools designed for something else and adapted to AI after the fact.

Camp A — Black-box apps

ChatGPT · Copilot · Gemini

General models behind a fixed product. Syrtis opens the box: a model per step, answers grounded in your knowledge, a full execution trace.

Camp B — Automation

n8n · Zapier · Make

Born for trigger→action ETL, where AI is a guest. At Syrtis, model execution and supervision are the organizing principle of the whole architecture.

Camp C — Frameworks

LangChain · Flowise · Dify

Syrtis shares the open-primitives lineage — and adds everything above it: entity, convergent executor, multi-store, versioning, monitoring, access.

PrincipleSyrtisBlack boxesAutomationFrameworks
LineageAI-native control planeConsumer SaaS productETL / trigger→actionLLM libraries / GUIs
Agent modelMulti-agent + blackboardNoneLinear, agents bolted on lateBuild it yourself
Knowledge / RAGNative, tunable nodesHidden / limitedExternal wiringPrimitives, you operate them
Data layerRelational · vector · graph · documentNoneConnectors, no storeYou provision it
Observability / auditWaterfalls · lineage · TraceNoneNon AI-aware logsDIY / add-on
Sovereignty / EU AI ActBy designDepends on the vendorNot a goalYour responsibility

Three years holding one direction

Sep 2024
v0.0

First end-to-end platform. Relational + vector + graph foundations. Multi-model from day one.

Jan 2025
v0.1

First usable Manager. Scenario / Card / Job / Node blocks. Parallelism. First knowledge flow.

Mar 2025
v0.2

Multi-path scenarios, conditions and loops, controlled determinism. Tunable chunking / embedding.

Jun 2025 →
v0.3.x

Graph-first editor, client SDKs, Registry, major execution upgrades, operational intelligence, multi-agent.

Out of prototype purgatory

Your demos work. Give them a reliable path to production.