← Skillful-Alhazen

Home

Skillful Alhazen

One agentic knowledge engine, many applications — each curating its own TypeDB database, all switchable from a single dashboard.

Prototype software — APIs, schemas, and skill interfaces are subject to change without notice.

“The duty of the man who investigates the writings of scientists, if learning the truth is his goal, is to make himself an enemy of all that he reads, and, applying his mind to the core and margins of its content, attack it from every side.”

— Ibn al-Haytham (Alhazen), 965–1039 AD

What is Skillful Alhazen?

Skillful Alhazen is an agentic curation system with knowledge-graph memory. An agent reads sources — papers, technology docs, job postings, your own brain dumps, a tabletop campaign — and builds structured understanding in a TypeDB knowledge graph that persists across sessions and grows with use. You talk; the agent curates. You never write queries or call APIs directly.

Three layers work together:

  • Agent — Claude Code, running locally and interactively.
  • TypeDB — ontological memory. The schema defines the concepts the agent reasons about; the data is what it has learned so far.
  • Skills — domain modules combining a TypeDB schema namespace, Python CLI scripts, and agent instructions. Each skill extends what the agent can do and remember in one domain.

One engine, many applications

The important shift: Skillful Alhazen is no longer a single notebook. It is a family of applications that share one engine. The same agent, the same TypeDB server, and the same dashboard host several independent knowledge products at once — kept separate by the database each one curates into. You move between applications by switching which database the dashboard reads.

Application TypeDB database What it curates
Core (Skillful Alhazen) alh_core / alhazen_notebook The notebook engine — memory, operator profile, schema, web search, skill-building
Deep Research alh_deep_research Literature corpora, technology investigations, hypothesis trends
Personal Assistant alh_personal The executive AI team — career, analyst, advisors, scribe, ops, chief of staff, coach
Mythras GM alh_mythras Persistent tabletop RPG campaigns

Each row is a self-contained product: install one without the others, and its database is provisioned on first use. The dashboard’s database switcher shows only the applications present on your server and hides the rest. Read the full model in The Multi-Database Model.

How to run it

Skillful Alhazen runs locally with Claude Code:

make build && claude

make build starts TypeDB and the dashboard and loads the schemas; claude opens the agent. See Getting Started for the full walkthrough.

The older persistent-service path (running inside OpenClaw on a Mac Mini or VPS) is deprecated and no longer supported. See Deployment for the retained reference.

Where to go next