Platform
Governance
Scoped keys, per-key limits, environments, teams and an audit log, so the security review has answers.
https://api.launchad.si/v1/usage -H "Authorization: Bearer $LAUNCHAD_KEY"Scoped keys. Models, agents and security scopes.
Limits. Per minute, per month, per environment.
Audit log. Who changed what, when and from where.
Keys
Keys you can
actually control
Keys are stored as hashes and shown once. Give each key scopes, limits, an IP allowlist and an expiry, and rotate it with a grace period.
IP allowlists CIDR ranges per key.
Rotation Replace a key without downtime.
Short-lived tokens For browser and mobile clients.
{ "key": { "requests": 1204, "tokens": { "used": 81240, "limit": 500000 } }, "rate_limit_rpm": 60 }
Also included
The details
that matter
Teams and roles
Owner, admin and member.
Environments
Separate dev and prod.
Two-factor sign-in
With replay protection.
Alerts
At 80% and 100% of a limit.
Data export
Everything as JSON.
Account deletion
After a 7-day grace period.
Related
launchad · getting started
# 1. point your OpenAI client at LaunChad
export OPENAI_BASE_URL=https://api.launchad.si/v1
export OPENAI_API_KEY=$LAUNCHAD_KEY
# 2. call any model, or start an agent run
curl $OPENAI_BASE_URL/agents/researcher/runs \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{"message":"What changed on our competitors' pricing pages?"}'Get started
Two lines of config.
The rest is built.
Keep your OpenAI client, change the base URL and the key. Limits, logs and guardrails are on from the first request.