Loop Engineering + Graph Engineering: Building a Compounding Second Brain with OKF-based LLM Wiki
Last Updated on August 25, 2026 by Editorial Team
Author(s): Rick Hightower
Originally published on Towards AI.
From Session Loops to Persistent Graphs: OKF, the Second Brain, and Compounding Agent Systems
Summary: This article shows how to stop paying for the same reasoning twice. It covers three foundations that decide whether knowledge survives a session. It covers an append-only event log that makes agent work visible, and a Git-native knowledge graph that holds both the why and the what. It then covers the ContextPack, which provides each new run with a bounded, ranked slice of that graph rather than a blank context. Every tool named here is open source, and the code is linked at the end.
The article argues that agent “session memory” fails in organizations because work is treated as private and temporary, causing teams to repeat decisions and lose institutional knowledge between runs. It lays out three key distinctions—harness engineering (control plane/evaluation guardrails), write authority (safe shared state via schema-enforced commits), and memory (separating procedural, working, and long-term institutional memory in the repo)—and explains how to make knowledge persistent by separating loop work from graph work. It then details how to structure an append-only event log, build a Git-native knowledge graph from Markdown/YAML under version control, and capture reasoning via project/system/data knowledge layers (PKC, SAC, DEKC). A central mechanism, the ContextPack, is presented as a bounded, typed, ranked subgraph passed to agents so each run starts with the right slice of context rather than a full dump or contextless retrieval. Finally, it describes how the “closing the loop” cycle uses deterministic boundaries to write corrections back into the graph, ties executable evaluations/graders into the same system, and emphasizes starting small with real repositories and workflows to ensure adoption and compounding improvement over time.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
