cog

Cog

A plain-text cognitive architecture for Claude Code — simple by design, so the model can reason over its own memory with the same Unix tools (`grep`, `find`, `git diff`) it already knows.

**[Documentation](https://lab.puga.com.br/cog)** | **[Why Text](https://lab.puga.com.br/cog/#/why-text)** | **[Credits & Inspiration](https://lab.puga.com.br/cog/#/credits)**

What is Cog?

Cog is a set of conventions — not code — that teach Claude Code how to build and maintain its own memory. You define the rules in plain text. Claude scaffolds the structure and follows them. The filesystem is the interface.

There is no server, no runtime, no application code. `CLAUDE.md` contains the conventions — how to tier memory, when to condense, how to route queries, when to archive. The skill files (`.claude/commands/*.md`) teach Claude specific workflows: reflection, foresight, housekeeping, self-evolution. Claude reads these instructions and follows them to organize, maintain, and grow a persistent knowledge base across sessions.

Everything is plain text [by design](https://lab.puga.com.br/cog/#/why-text). Not as a compromise — because plain text is what makes this work. Memory files are just markdown, which means Claude can `grep` for patterns, `find` what changed, `wc` to check file sizes, and `git diff` to see what the last pipeline run touched. The same Unix tools that make Linux powerful make Cog's memory observable and maintainable.

Cog is a learning tool — an experiment in watching how a memory architecture evolves when given clear conventions and self-observation capabilities. You set the rules, Claude scaffolds the structure, and the pipeline skills refine the conventions over time. The model doesn't evolve — it follows whatever rules it finds. The rules are what change. Every decision is visible. Every rule is editable. Every change is in the git log.

Quick Start

Requires [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview).

...