SafeAgentDB – Isolated databases for every AI agent branch

zarskia92 pts0 comments

GitHub - Aidan945/SafeAgentDB: Isolated databases for every AI agent branch. Build, test, and migrate in parallel. Production stays untouched. · GitHub

/" data-turbo-transient="true" />

Skip to content

Search or jump to...

Search code, repositories, users, issues, pull requests...

-->

Search

Clear

Search syntax tips

Provide feedback

--><br>We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Cancel

Submit feedback

Saved searches

Use saved searches to filter your results more quickly

-->

Name

Query

To see all available qualifiers, see our documentation.

Cancel

Create saved search

Sign in

/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up

Appearance settings

Resetting focus

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

Aidan945

SafeAgentDB

Public

Notifications<br>You must be signed in to change notification settings

Fork

Star

main

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>12 Commits<br>12 Commits

skills/safeagentdb

skills/safeagentdb

.gitignore

.gitignore

LICENSE

LICENSE

README.md

README.md

View all files

Repository files navigation

SafeAgentDB

Database safety infrastructure for AFK agentic development.

SafeAgentDB is built for serious vibe coders shipping real products with a team — whether your teammates are people, AI agents, or both. Once you have many branches in flight at the same time, one shared database becomes the thing everyone breaks. SafeAgentDB gives every branch and PR a live preview URL backed by its own isolated database, so agents can run migrations, hydrate realistic data, and test real app behavior without risking production, corrupting shared development data, or stepping on each other.

Built first for Supabase + Vercel + GitHub Actions , with guidance for adapting the same infrastructure pattern to other stacks.

Install The Skill

SafeAgentDB is listed on skills.sh, the open agent skills directory, and on ClawHub, the OpenClaw skill registry.

Install with the skills CLI:

npx skills add https://github.com/Aidan945/SafeAgentDB --skill safeagentdb

Shorthand:

npx skills add Aidan945/SafeAgentDB --skill safeagentdb

You can also target a specific agent:

npx skills add Aidan945/SafeAgentDB --skill safeagentdb --agent cursor<br>npx skills add Aidan945/SafeAgentDB --skill safeagentdb --agent codex<br>npx skills add Aidan945/SafeAgentDB --skill safeagentdb --agent claude-code

Or install with OpenClaw:

openclaw skills install safeagentdb

Use The Skill

After installing, start your agent in the project where you want SafeAgentDB installed and say:

Use the safeagentdb skill.

Inspect this project, then set up SafeAgentDB database safety infrastructure for it. Review your plan with me before making changes.

The skill handles the rest: inspecting your stack, adapting to non-default setups, asking before touching credentials, and never committing secrets.

What SafeAgentDB Enables

SafeAgentDB helps AI agents set up:

Local Docker database development

A persistent develop/staging database

Branch-specific preview databases with live preview URLs

Safe migration flow: checks before merge, preview-only feature migrations, production deploys from main

Optional hydration of realistic data, auth users, and storage into previews

Vercel preview env wiring with automatic redeploys after env changes

Cleanup on PR close plus scheduled orphan cleanup, with persistent design/demo environments skipped

Dry-run provisioning and a committed branching architecture doc as the project's source of truth

The result: agents can work in parallel, publish PRs, and give users live URLs to test without touching production or shared development data.

Default Stack

The default templates are built for:

Supabase for Postgres, Auth, Storage, migrations, and database branches

Vercel for production, staging, and preview deployments

GitHub Actions for branch and PR automation

If your project uses a different database, deployment platform, or CI provider, SafeAgentDB should be treated as a conceptual model. The AI agent should inspect your codebase, explain what needs to change, and adapt the pattern to your infrastructure.

Skill Contents

Everything the agent needs is bundled inside the skill:

skills/<br>safeagentdb/<br>SKILL.md<br>references/<br>setup-process.md<br>credentials.md<br>data-hydration-policy.md<br>local-development.md<br>non-standard-stacks.md<br>troubleshooting.md<br>agent-operating-rules.md<br>agent-packaging.md<br>templates/<br>branching-config.example.json<br>package-scripts.json<br>package-dev-dependencies.json<br>docs/<br>database-branching.md<br>scripts/<br>supabase/<br>ci/<br>.github/<br>workflows/<br>agent-instructions/<br>AGENTS.md<br>CLAUDE.md

Safety...

safeagentdb agent skill skills database aidan945

Related Articles