epistemic

Open-source swarm intelligence for the open web. Run 10,000+ AI agents reading the internet with epistemic discipline. Every claim is evidence-backed. Every source is scored.

A sycophantic tool for preventing worse sycophancy.

The trust layer for AI agents.

Deterministic reasoning assurance engine for AI agents. Fast (<5ms), zero-cost verification. Best-in-class for arithmetic, logic, and hallucination detection.

PRISM — Epistemic Graph RAG with Spreading Activation. Novel retrieval that understands how knowledge relates, not just what it says.

The first agent runtime with built-in epistemic honesty

Semantic and visual environment for tasks, knowledge, research and agents — a second brain that interprets ASC. (Revival ~15 years later.)

Experimental local-first agent template with provenance-oriented logging. Work in progress — not a finished product.

Model-agnostic trust protocol for calibrated, auditable AI

Multi-Agent System course at University of Groningen 16/17 (Master Artificial Intelligence)

Simple Texpattern CMS theme to interlink multiple-user content (articles) through key words, related articles, categories, the search function, and links to author pages listing authors' articles. Designed to promote collaborative, project-based relational learning but could be used for IndieWeb selfdogfooding purposes. Sample images in the wiki…

A Claude skill that runs any claim, post, or headline through a ten-step epistemic checklist: what's actually being asserted, and how much confidence does it deserve? Companion to the essay "The Internet Is Probably Lying to You."

A vibe-coded web version of my Dissertation for educational purposes.

One binary distinction forces K₄. Machine-verified derivation in Agda --safe --without-K, zero postulates.

Um estudo sobre Filosofia da Lógica; Overview do método de Newton da Costa, Gödel, Morgan, Dummett, Frege, Leibniz, Peirce, Orman Quine, Ludwig Wittgenstein

Computable Embodied Constructor Theory (cECT) operational engine with two companion papers, Zenodo DOIs, and reproducible example run.

Epistemic governance framework for Elixir. Claims, evidence, EIG scoring, 7-layer adversarial defense, experiment loops. 18 modules, 6718 lines, 241 tests.

A multi-layer verification system for AI-generated analysis that exploits documented behavioral differences across language models to detect hallucination, simulation drift, and epistemic failures.

Ruby framework for building contracts-native applications, companions, and agent-aware systems, declarative dependency-graph runtime for business logic