opencortex
jd2005l 제작
Web & Frontend Development요약
Self-improving memory architecture for OpenClaw agents.
설명
이 스킬이 하는 일
Memory architecture system for OpenClaw agents. Structures memory into purpose-specific files and installs nightly distillation and weekly synthesis cron jobs that route daily work into permanent knowledge. Sensitive features (voice profiling, git backup, infrastructure collection) are off by default and require explicit opt-in.
Automates knowledge compounding through scheduled cron jobs rather than relying on manual memory management or flat context files.
사용 시점
- Setting up a new OpenClaw agent with organized memory from day one
- Stopping an agent from re-asking questions or re-learning preferences it already encountered
- Automatically backing up agent memory to git with secrets scrubbed before each push
- Reviewing how much an agent has learned over time using compound growth scores
- Recovering sub-agent work into the main memory pipeline via nightly distillation
예시 워크플로
User asks: Set up memory architecture for my OpenClaw agent
- 1
Runs
clawhub install opencortexfrom the workspace root to download the skill - 2
Runs
bash skills/opencortex/scripts/install.shand selects optional features (vault, git backup) - 3
Installer creates the file hierarchy (SOUL.md, MEMORY.md, USER.md, memory/ subdirs) without overwriting existing files
- 4
Cron jobs for nightly distillation (3 AM) and weekly synthesis (Sunday 5 AM) are registered
- 5
Runs
bash skills/opencortex/scripts/verify.shto confirm files and cron jobs are active
Structured memory files in place, principles enforced, nightly and weekly cron jobs running, agent begins compounding knowledge each session
요구 사항
- OpenClaw 2026.2.x+ installed
- ClawHub CLI installed
설치
clawhub install jd2005l/opencortexCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.