Coming soon — join the early access list

Give your agents the right keys.
Nothing more.

Agent Keys give AI agents scoped, time-limited API credentials with spend caps and endpoint restrictions — enforced transparently at the proxy. Your agent doesn't change a line of code.

The problem today

Unlimited spend

Agents carry your full API key. One runaway loop and you're staring at a $500 OpenAI bill.

No expiry

CI keys live forever. A leaked key from a test run three months ago is still valid today.

No scope

Your agent only needs to call /v1/chat/completions. But it has access to everything.

Define the policy. VaultProof enforces it.

Your agent keeps its existing proxy URL. You add a policy. The proxy does the rest.

agent.policy.yaml

name: "my-coding-agent"
key: "openai/production"

# What the agent can do
endpoints:
  - "/v1/chat/completions"
  - "/v1/embeddings"

# Hard limits
budget: $1.00  # per run
ttl: "10m"    # self-destructs

# Auto-reset between runs
reset_on_complete: true

What happens at runtime

Agent starts, uses its normal proxy URL

No code changes. The agent calls api.vaultproof.dev/v1/openai as usual.

VaultProof reads the agent's policy

Every call is checked against allowed endpoints, remaining budget, and TTL expiry.

Call is proxied or blocked

Valid calls go through. Attempts outside the policy return a clear error — no silent failures.

TTL expires, key is gone

The scoped key self-destructs. No cleanup step. No leftover credentials.

What you control

TTL

Set a duration — 5 minutes, 1 hour, 24 hours. The key expires automatically. No manual revocation needed.

Spend cap

Set a dollar limit per run. Once hit, the key is blocked. No surprises on your OpenAI bill at the end of the month.

Endpoint restrictions

Whitelist exactly which API endpoints the agent can call. Everything else is blocked at the proxy.

Auto-reset

Each agent run gets a clean credential slate. Spent budget and state don't carry over between runs.

Full audit log

Every call the agent makes is logged — endpoint, tokens, latency, cost. Know exactly what your agent did.

Works in CI

Agent Keys are headless by default. No interactive auth, no session tokens. Drop them straight into GitHub Actions.

Built for how agents actually run

CI / CD

Pipeline runs

Each CI run gets a fresh scoped key. It expires when the job finishes. No leftover credentials sitting in your repo secrets.

Eval harnesses

LLM evals

Run hundreds of eval cases with a capped budget per suite. Know the eval can't spend more than you've budgeted, no matter what.

Multi-agent

Agent orchestration

Give each sub-agent in your pipeline its own scoped key. The orchestrator controls the budget. Sub-agents can't exceed their allocation.

End users

User-facing agents

Give your users agents backed by your keys, scoped so they can't exceed their plan limits. No risk of one user blowing your entire API budget.

Early access

Be the first to try Agent Keys

We're building this with a small group of early users. If you're running agents in CI or building multi-agent systems, we want to talk to you.