Doug Finke's Experiment: Giving AI a Persistent Memory

Episode 1 · Doug Finke's Experiment: Giving AI a Compounding Personal Knowledge Base (2026-09-08, 3 posts)

Microsoft MVP Doug Finke is running a public experiment using a minimal harness of just five tools, Markdown, and an LLM to let agents accumulate knowledge instead of forgetting after each session, with a live stream scheduled for Thursday.

• Live experiment: a tiny harness, five tools and Markdown to give your AI a personal knowledge library — dfinke · 2026-09-08
• Doug Finke to Livestream 'Own Your Intelligence: Personal AGI' Experiment — dfinke · 2026-09-10
• Five tools, Markdown, one LLM: making agents compound knowledge you own — dfinke · 2026-09-10

Episode 2 · 16-Time Microsoft MVP Live-Tests a Minimal 'Personal AGI' (2026-09-10, 9 posts)

On September 10–11, 16-time Microsoft MVP and creator of ImportExcel/PSAI, Doug Finke, will demo his experiment "Own Your Intelligence: Personal AGI" live at the Agentic AI community Meetup in New York, tackling the problem of AI sessions being throwaway—agents losing all knowledge the moment a session ends.

Confirmed

• Doug Finke is a 16-time Microsoft MVP and author of ImportExcel and PSAI; the livestream is an Agentic AI community Meetup event in New York.
• The experimental setup is deliberately minimal: no frameworks, just a small harness, five basic tools, Markdown files, and one LLM.
• The core idea is "your work becomes a library, and the AI just needs to find the right book at the right moment"—turning your work output into a knowledge base that can accumulate, organize, and be retrieved over time, giving the agent long-term memory instead of resetting every session.
• Finke describes the experiment as "no frameworks, no magic"—just enough mechanism to observe whether the AI starts behaving as if it has a genuine "brain" that belongs to the user, with the agent running on the user's own infrastructure, available anytime.

Why it matters

Most mainstream AI assistants still lack the ability to accumulate personal knowledge across sessions. This experiment shows a minimal viable path without heavy frameworks, validating that "minimal tools + Markdown" is enough to give an agent persistent memory—valuable for both the personal knowledge management and agent development communities.

• 16x Microsoft MVP livestreams Personal AGI: five tools and Markdown to make agents compound knowledge — dfinke · 2026-09-10
• Personal AGI experiment: a tiny harness, five tools, Markdown, one LLM to give agents memory — dfinke · 2026-09-10
• No frameworks, no magic: turning your work into a library the AI can actually search — dfinke · 2026-09-10
• Live Experiment: Building a Personal AGI with a Markdown Knowledge Library — dfinke · 2026-09-11
• Microsoft MVP Demos Personal AGI: Five Tools, Markdown and One LLM — dfinke · 2026-09-11
• A minimal agent memory harness: five tools, Markdown, one LLM — no frameworks — dfinke · 2026-09-11
• 16x Microsoft MVP Demos a Minimal Harness That Lets AI Agents Own Your Knowledge — dfinke · 2026-09-11
• Agent Forgets Everything After Each Session? A Minimal Fix, Demoed Live — dfinke · 2026-09-11
• 'No Frameworks, No Magic': Turn Your Work Into a Library AI Can Search — dfinke · 2026-09-11