v0.2.0 · MIT
Schema-as-code memory for AI agents in Obsidian: typed cards, entity dedup, link repair, update-in-place, and Ebbinghaus decay. Plain Markdown you own — a Claude Code skill.
v2.9.7 · MIT
A Claude Code plugin that gives Claude persistent memory across sessions — stores lessons and decisions as markdown in your Obsidian vault, searches them with SQLite FTS5, and mines past transcripts automatically.
— · AGPL-3.0
The agentic workspace where people and agents work together in the loop.
v4.9.2 · MIT
Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts, efficiency scores, git-aware suggestions — all local, zero config.
— · MIT
Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates. Markdown library (loop-graph), not a framework.
— · MIT
Lives inside your Claude Code session. Capture work as structured experience, then render resumes, Korean cover letters, interview answers, and project ideas from it.
v0.5.0 · MIT
Claude Code plugin that shows live session status (⚡ running / 💤 idle / 🔴 attention) in your iTerm2 tab title — no config needed, just install and go.
v1.6.0 · MIT
Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills
v0.1.0 · Apache-2.0
Claude Code Plugin for Self-maintaining research knowledge graph for Claude Code + Obsidian
v2.0.4-beta · no license
Specification-driven workflow system for AI-assisted development - break large projects into manageable 2-4 hour sessions with 15-30 tasks each.