seyio91/ai-memory-system
Markdown-only persistent memory shared by Claude Code, OpenAI Codex CLI and Antigravity — no vector DB, no daemons, no MCP server. Just files, hooks and bash 3.2 scripts.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit seyio91/ai-memory-system/agents ./rig-ai-memory-system/agents $ npx degit seyio91/ai-memory-system/commands ./rig-ai-memory-system/commands $ npx degit seyio91/ai-memory-system/skills ./rig-ai-memory-system/skills
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit seyio91/ai-memory-system/skills/design-brainstorm .claude/skills/design-brainstorm $ npx degit seyio91/ai-memory-system/skills/project-scan .claude/skills/project-scan $ npx degit seyio91/ai-memory-system/skills/skill-audit .claude/skills/skill-audit
$ curl -fsSL --create-dirs -o .claude/agents/auditor.md https://raw.githubusercontent.com/seyio91/ai-memory-system/main/agents/auditor.md $ curl -fsSL --create-dirs -o .claude/agents/azure-infra-engineer.md https://raw.githubusercontent.com/seyio91/ai-memory-system/main/agents/azure-infra-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/devops-engineer.md https://raw.githubusercontent.com/seyio91/ai-memory-system/main/agents/devops-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/kubernetes-specialist.md https://raw.githubusercontent.com/seyio91/ai-memory-system/main/agents/kubernetes-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/terraform-engineer.md https://raw.githubusercontent.com/seyio91/ai-memory-system/main/agents/terraform-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/validator.md https://raw.githubusercontent.com/seyio91/ai-memory-system/main/agents/validator.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (3)
Subagents (6)
| auditor model: opus | Use to audit one project's memory.md claim by claim against its repo and read-only APIs, returning a verdict and evidence per checkable claim without modifying anything. |
| azure-infra-engineer model: sonnet | Use when designing, deploying, or managing Azure infrastructure with focus on network architecture, Entra ID integration, PowerShell automation, and Bicep IaC. |
| devops-engineer model: sonnet | Use this agent when building or optimizing infrastructure automation, CI/CD pipelines, containerization strategies, and deployment workflows to accelerate software delivery while maintaining reliabili |
| kubernetes-specialist model: sonnet | Use this agent when you need to design, deploy, configure, or troubleshoot Kubernetes clusters and workloads in production environments. |
| terraform-engineer model: sonnet | Use when building, refactoring, or scaling infrastructure as code using Terraform with focus on multi-cloud deployments, module architecture, and enterprise-grade state management. |
| validator model: opus | Use to independently verify a completed plan phase and review code changes without modifying the repository under test. |
Slash commands (21)
/activity/archive-cleanup/checkpoint-archive/checkpoint/lint-memory/list-skills/new-initiative/new-plan/new-project/pin/plan-archive/plan-done/promote-memory/reindex/start/state/sync-system/task/test-system/threads/todo-archive
Similar rigs
orban/intent-layer
Custom skills for Claude Code CLI - Intent Layer setup and maintenance
Automator 4.6k tok · · Q18
piomin/claude-ai-spring-boot
Claude Code template for Spring Boot and cloud native ecosystem
Orchestrator 1.0k tok · · Q0
vantt/skillstation
A local hub that curates your agent skills and serves the right one to Claude Code, Codex and Gemini over MCP.
Pragmatist 6.6k tok · · Q8
requix/kiro-team
Multi-agent orchestration for Kiro CLI - coordinate specialized AI agents to tackle complex tasks through planning, parallel execution, and validation.
YOLO Cowboy 189 tok · · Q0