Rebar — Structural Memory for Claude Code

Rebar is a structural memory framework for Claude Code — a solo-built open-source tool that solves one of the most frustrating problems in AI-assisted development: context loss between sessions. As the sole architect and engineer, I designed and built a system of 26 slash commands, 4 knowledge systems, and 6 background agents that give Claude Code persistent, compounding project knowledge across every session.

Claude Code is a powerful AI coding tool, but it forgets everything between sessions. Every time you start a new session, you have to re-explain your architecture, your conventions, your in-progress work, and your project context — from scratch. For developers working on complex, long-running projects, this meant hours of repeated context-setting. The challenge: build a persistent memory layer that captures, validates, and compounds project knowledge automatically.

I built Rebar as a fully solo project — architecture, engineering, documentation, and deployment. The system gives Claude Code a structured memory layer through four interlocking components.

26 slash commands covering project context capture, dev workflow management, wiki operations, and advanced agent orchestration. Commands like /create, /discover, /improve, and /sync give developers immediate, intuitive control over their project's memory — no configuration required. Clone the repo and they just work.

Four specialized knowledge stores that give Claude Code structured, queryable memory: expertise.yaml tracks project state and architecture decisions; .claude/skills/ holds tactical playbooks for recurring workflows; wiki/ stores durable long-form knowledge; and meta-improve-log manages template patch history. Each system is designed to be read and updated by Claude automatically during sessions.

Six Paperclip-powered background agents that run autonomously to keep project knowledge current: validating expertise entries against live code, processing wiki intake, routing issues to the right owners, and running scheduled freshness checks. The agents ensure Rebar's knowledge stays accurate over time without manual maintenance.

The /improve command runs a validation loop that checks every observation in expertise.yaml against the actual live codebase. It promotes observations that are confirmed true, discards what's stale, and flags conflicts for review. Over time, the project's memory gets more accurate and more useful — context that compounds rather than decays.

26 slash commands for project context capture, wiki management, and agent orchestration

4 structured knowledge systems (expertise.yaml, skills, wiki, meta-improve-log)

6 Paperclip-powered background agents for automated knowledge validation and maintenance

Self-validating /improve loop that promotes accurate context and discards stale knowledge

Zero-config installation: clone the repo and commands work immediately in Claude Code

Fully open source (MIT License) — solo-built: architecture, engineering, and documentation

Claude Code slash command framework, Paperclip agent orchestration, YAML-based structured knowledge storage, Git-native workflow integration, and open-source architecture. Built entirely as a solo project — system design, engineering, documentation, and deployment.