getlaunchbuddy

LaunchBuddy for AI agents

LaunchBuddy answers: What is blocking this launch, what should happen next, and can you make it for me?

Public setup, access, and safety documentation: launchbuddy.com/agents

npx getlaunchbuddy install --all
npx getlaunchbuddy connect

Then ask your agent:

/launchbuddy assess https://example.com
/launchbuddy plan
/launchbuddy make the top recommended asset
/launchbuddy reassess

The installer adds one portable LaunchBuddy router skill and an MCP bridge to Claude, Codex, and Cursor. The bridge keeps the installer and project-context handoff local while assessment, account ownership, plans, approvals, billing, and asset state remain hosted by LaunchBuddy.

Access model

• Assessment and shareable reports can run anonymously.
• connect is free identity and project continuity. It never creates checkout or a subscription.
• Connected users can save projects, create the cached assessment-derived plan, preview the top recommended asset, and reassess.
• The first eligible creation can unlock one assessment-bound, one-render agent trial; a paid entitlement unlocks broader execution access.
• Paid execution always requires explicit review/approval. LaunchBuddy never auto-charges or publishes from an assessment.
• Existing paying users connect their existing account and keep their current access; they do not buy again.

Commands

install --all   Install the router skill and MCP bridge
connect         Approve a free device connection in the browser
login           Alias for connect
status          Show local connection state
logout          Remove local credentials
mcp             Run the local stdio-to-hosted MCP bridge

Access tokens are short-lived, refresh tokens rotate, and the server stores token hashes rather than raw tokens. Local credentials are written with user-only file permissions.