Open Source Toolkit

Skillful-Alhazen

An AI-powered ontological notebook for systematic research. Build knowledge graphs from papers, documents, and data using Claude Code agents backed by TypeDB.

Architecture

Agent Layer

Claude Code orchestrates the curation pipeline — reading documents, calling skills, managing workflow, and reasoning about results.

Knowledge Layer

TypeDB provides a typed, schema-enforced knowledge graph. Entities, relationships, and rules — not just vectors and embeddings.

Skills Layer

Modular skill modules handle specific tasks — search APIs, document parsing, entity extraction, graph queries, and report generation.

Skills

Skill Category Description
alhazen-core Core Infrastructure plugin — starts TypeDB + dashboard via Docker, loads the foundational schema. Required first-install for all other skills.
typedb-notebook Core Remember, recall, organize, and query knowledge in the Alhazen TypeDB knowledge graph — and power the hub's database switcher.
agentic-memory Core TypeDB-backed ontological memory — operator profiles, long-term memory claims, session episodes, and three-stage schema-driven retrieval with semantic search.
web-search Core Web search via a self-hosted SearXNG metasearch engine aggregating Google, DuckDuckGo, Bing, and other engines — no API key required.
curation-skill-builder Core Design and implement new domain-specific knowledge skills using the 6-phase curation pattern (Foraging → Ingestion → Sensemaking → Analysis → Reporting).
scientific-literature Deep Research Multi-source scientific literature search and ingestion — Europe PMC, PubMed, OpenAlex, bioRxiv/medRxiv — with semantic search and thematic clustering.
tech-recon Deep Research Goal-driven technology investigation — interview, discover, ingest, analyze, and visualize competing systems against user-defined success criteria.
literature-trends Deep Research Abductive argumentation-based trend analysis that traces how explanatory hypotheses evolve over time within a tagged literature thread.
dismech-notebook Deep Research GLAV bridge mapping the DisMech rare-disease knowledge base into the Alhazen notebook memory system for cross-skill integration.
career Personal Assistant The career graph — people, collaborators, projects, and the opportunity pipeline, with skill-gap and learning-plan analysis.
analyst Personal Assistant Research analyst that frames decision-linked questions, commissions the deep-research engines, and gates findings with multi-engine consensus and verification.
advisor Personal Assistant A persona board of advisors that debates a decision then converges — calibrated pushback, bias checks, scenario stress-tests, and a decision journal.
scribe Personal Assistant Writing in the operator's voice for the operator's audience — voice profile, reader personas, and dimension-scored draft feedback.
ops Personal Assistant The operational powerhouse — recurring briefs, a personal stakeholder CRM, meeting prep, two-way commitment tracking, and standing monitors.
chief-of-staff Personal Assistant Read-only capstone — a synoptic daily agenda and weekly review orchestrating the analyst, advisor, scribe, ops, and career skills.
coach Personal Assistant Personal health and fitness monitoring — ingest Apple HealthKit data, track goals, detect regressions, manage appointments and lab results.
mythras-gm Mythras GM Persistent tabletop RPG Gamesmaster — runs Mythras Imperative campaigns with characters, encounters, worldbuilding, and session journal in TypeDB.

Documentation

Getting Started

Skillful-Alhazen is open-source and under active development:

# Clone the core library
git clone https://github.com/sciknow-io/skillful-alhazen.git
cd skillful-alhazen
make build