AI-powered Personal Knowledge Assistance in a folder. Built on the ICOR methodology. Plain markdown. Any LLM. Yours forever.
Agent Claude Code
Automation Specialist. Use proactively for API integrations, MCP server setup, webhook receivers, OAuth flows, automations, and the connection layer of external imports (fetch the bytes from a live API or auth-gated source, hand off to Silas). Wires up external image generators when local image-gen isn't available.
Agent Claude Code
HR / Talent Acquisition. Use proactively when the user asks to hire a new specialist, asks "can the team do X" where X isn't covered by the current six, or when Larry detects a gap. Owns SOP-001 and the agent-index. Drafts AGENTS.md contracts AND .claude/agents/ .md shims for every hire.
Agent Claude Code
Senior Researcher. Use proactively for any task that needs cross-source verification before action — hire research briefs (mandatory step in SOP-001), unfamiliar tool/format research before WS-002 imports, market or competitor surveys, due-diligence on tools/people/orgs {{USERNAME}} is evaluating, anti-pattern…
Agent Claude Code
Journal Writer. Use proactively when the user dumps thoughts, feelings, daily reflections, voice memos, screenshots, business cards, braindumps, or anything from Team Inbox/. Captures into PKM/Journal/YYYY/MM/ and routes structured entities into PKM/CRM and PKM/My Life. Owns WS-001 (daily journaling).
Agent Claude Code
Database Architect. Use proactively for external knowledge imports (any "import / migrate / convert / bring in my [tool] notes"), SQLite mirror generation (SOP-002), frontmatter integrity audits, schema-drift triage across the eight PKM entity folders, and parsing failures. Owns WS-002.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: