Structured knowledge
for AI agents
that actually remember.
Kernal is a local-first knowledge graph that turns your conversations into connected intelligence — so every meeting compounds instead of evaporating. Open source. MCP protocol. Your machine, your models.
The Problem
Your agents forget everything.
Every conversation, every meeting, every email — rich with context about who knows who, what was decided, and why. But your AI agent starts every session from zero.
RAG gets you 80%. You can search your docs and find relevant snippets. But try asking “Who introduced Sarah to the Hydro project and what was their concern about the timeline?” Vector search fails. Structure succeeds.
Kernal extracts entities, relationships, and temporal context from natural conversation — automatically. Every transcript processed makes the graph smarter.
Proof of Concept
Now imagine this is
your client portfolio.
Fifty meetings. A hundred and ninety people. Fifteen hundred relationships. Every name, every connection, every promise your team has ever made — structured and queryable by your AI agent.
Real production data from enterprise consulting engagements.
Graph Intelligence
Ask questions that
search can't answer.
Vector search finds documents. Kernal traverses relationships.
Philosophy
An agent without context is a chatbot.
An agent with context is an employee.
AI models get better every quarter. But a better model without your context still can't answer “Who introduced Sarah to the Hydro project and what was their concern about the timeline?”
Context is the durable layer. The thing that makes AI useful in professional services isn't the model — it's the structured knowledge the model can reason over. Better models make Kernal more valuable, not less.
If a product's value can be rendered obsolete by a better version of Claude or GPT, it lacks a structural moat. Kernal passes this test. The graph deepens with every conversation, and no model can replace what it contains.
Architecture
Five layers of intelligence.
Every entity connects to every other via the relationship graph. The graph is the product.
Capabilities
What Kernal does.
Entity Extraction
Drop in a transcript. Kernal extracts people, organizations, topics, and the relationships between them. No templates. No configuration. Just structure.
Graph Search
Not just keyword matching. Query across relationships: “Who at Nordic Tech has influence over the SAP decision?” Kernal traverses the graph.
MCP Protocol
Plug Kernal into Claude, Cursor, or any MCP-compatible tool. Your agent gets structured context about your world — people, relationships, history — in every conversation.
Meeting Prep
Before any call, Kernal surfaces: who you're meeting, their org chart position, recent interactions, open action items, and strategic context. Automatically.
Data Sovereignty
Your graph. Your machine.
Your models.
Most AI knowledge tools send your data to someone else's servers. Kernal doesn't. No DPA needed. No data residency concerns. No vendor training on your client intelligence.
Local processing
Entity extraction runs via Gemma 4 on your machine. Your transcripts, client names, and deal details never leave your infrastructure.
Local storage
Your knowledge graph lives in a SQLite file on your device. No cloud database. No vendor access. Full portability.
Open protocol
MCP is an open standard, not a proprietary API. Connect Kernal to Claude, Cursor, or any compatible tool. No vendor lock-in.
Built For
Professional services that
run on relationships.
Kernal is designed for people whose work depends on knowing who connects to whom, what was said, and what it means.
Executive Search
Map candidate networks, board relationships, and organisational dynamics. Know who knows who before the first call.
Management Consulting
Build institutional memory across engagements. Every meeting, every stakeholder, every strategic decision — structured and searchable.
Strategic Advisory
Track deal pipelines, stakeholder influence, and client goals across your portfolio. Your AI agent knows the full picture.
Law Firms
Matter context that compounds. Client relationships, precedent connections, and engagement history — locally stored, never shared.
Get Started
Two paths. Same graph.
Self-hosted (free, open source)
Install locally with one command. Your machine, your data, zero dependencies.
Then add Kernal as an MCP server in Claude Desktop or Claude Code.
Kernal Cloud (managed)
No install needed. Connect directly from Claude and start building your graph in seconds. 7-day free trial, then from $9/mo.
Talk naturally
Start having conversations. Kernal extracts and connects entities automatically. The graph compounds.
Community
Join the builders.
Book a demo
See Kernal in action. 30 minutes with the founder to explore how it fits your workflow.
Book a meeting →SubStack
Technical deep dives on agent architecture, knowledge graphs, and the MCP ecosystem.
Subscribe →Build agents
that remember.
See how Kernal works with your data. Book a 30-minute demo or start building with the open-source core.