Get started
Quickstart
Store your credentials in an access bundle and connect the agents that use them.
Why use Agent Vault?
Learn more about the problem Agent Vault addresses.
How it works
Understand the Agent Vault mental model.
Plan your setup
Get a recommended setup for what you’re building.
Guides
Set up Agent Vault for where your agents run.Sandboxes
Modal
Run an Agent Vault proxy in each Modal sandbox so the agent never has access to a credential.
Daytona
Run an Agent Vault proxy beside each Daytona sandbox so the agent never has access to a credential.
Docker
Run an Agent Vault proxy beside each agent container so the agent never has access to a credential.
Messaging gateways
Hermes gateway
OpenClaw gateway
Your own code
Your own agent
Launch your custom agent with Agent Vault so it can call HTTP APIs and MCP servers without having access to their credentials.
Local development
Claude Code
Codex
OpenCode
Hermes Agent
OpenClaw
Concepts
Access bundles
Lists of services that AI agents can access during a session.
Services
Anything an AI agent talks to during a session, such as an API or an MCP server.
Variables
Values you store once and use in any service in Agent Vault.
Skills
Instructions you keep in Agent Vault and install for agents you start with an access bundle.
Sessions
Time-bound grants that let AI agents access services without holding real credentials.
Create sessions with the CLI
Start an agent from cron, a container, or CI, with a new session for each run.
Create sessions with the API
Create a session for each agent run from your own code.
Session logs
A record of every request an AI agent makes, stored encrypted.
Proxies
Forward proxies that intercept an AI agent’s requests and attach real credentials on the way out.
Access control
Understand how permissions work in Agent Vault.
Reference
CLI reference
Every flag of
infisical agent-vault proxy and infisical agent-vault run.