Athenaeum
Subconscious recollection layer for AI agents — an append-only knowledge pipeline where trust emerges from a Wikipedia-style footnote graph embedded in the wiki structure itself.
Practice what you preach. I coach teams on shipping AI products; these are the products I ship myself. Each one solves a problem I actually had — cost control on agent workflows, personal knowledge memory, forecasting from sparse data, automated ops. Some are open source, some are in pilot, all are running in production.
Subconscious recollection layer for AI agents — an append-only knowledge pipeline where trust emerges from a Wikipedia-style footnote graph embedded in the wiki structure itself.
Data-driven decision making for enterprise innovation portfolios — Monte Carlo simulations for financial modeling under uncertainty.
Open-source tiered scheduler for Claude agent workflows. Cheap scripts first, cheap models next, expensive reasoning only when items actually need it.
Personal Chief of Staff built on NanoClaw — manages email, calendar, bug-fixing, and the automated build pipeline. 47+ open-source skills across communication, scheduling, development, and infrastructure.
Agent-discoverable estimation service for uncertain-variable forecasting. Provides structured probability estimation via REST API and MCP server, powering both Krobar.ai and standalone agent workflows.
Kromatic's full innovation-coaching knowledgebase — frameworks, client engagements, and methodologies — exposed as a Model Context Protocol server for AI agents.