Open Source

Clarity Framework

An agentic intelligence framework for technical engagements. Gives any engineer full project context on day one and grows smarter throughout the engagement.

Built on Karpathy's LLM Wiki Pattern

Andrej Karpathy proposed that the best way to use LLMs is to build a personal wiki — structured knowledge that the model reads before answering. Clarity extends this pattern with structured operational data (expertise.yaml), behavioral memory (Claude's auto-memory), and a self-learn loop that validates observations against live state.

Three Knowledge Systems

expertise.yaml

Operational Data

Project state, API gotchas, results, configuration. Structured YAML updated by /se:* commands. The agent's persistent brain — capped at 1000 lines.

.claude/memory/

Behavioral Rules

User preferences, guardrails, process rules. Markdown with frontmatter, auto-managed by Claude. Persists across conversations.

wiki/

Durable Knowledge

Synthesized patterns, decisions, people, concepts. Obsidian-compatible markdown with [[wiki links]]. Updated by /se:wiki-* commands.

9 SE Commands

CommandWhat It Does
/se:createCreate a new client with config files
/se:discoverPhase 0 auto-generation, seeds expertise.yaml
/se:briefStandup/handoff summary from expertise.yaml
/se:self-improveValidate observations, integrate confirmed facts
/se:checkDesign guidelines compliance check
/se:wiki-ingestProcess raw/ files into wiki pages
/se:wiki-fileFile a conversation insight as wiki page
/se:wiki-lintHealth check: orphans, broken links, stale pages
/se:meetingIngest meeting notes into notes.md and expertise.yaml

The Self-Learn Loop

1

Observe

Every /se:* command appends raw observations to unvalidated_observations

2

Validate

/se:self-improve checks each observation against current live state

3

Promote

Confirmed facts get promoted into the relevant expertise section

4

Compound

Knowledge grows and compresses. The system gets smarter with every session

Want us to set it up for you?

We implement Clarity for teams — custom client templates, wiki seeding, command tuning, and training.

Get in Touch