Agents
Trust infrastructure for agents that act.
Agents are easy to launch. Trustworthy agents are not.
Verifiable identity, scoped authority, and receipts for every trusted action.
Agent frameworks handle tools and execution. NEUS handles trust before action.
Five questions, one receipt
Identity tells you who an agent is. It does not tell you what the agent is allowed to do. NEUS covers both — in one receipt anyone can check.
- Who is this agent?
- Who controls it?
- What is it allowed to do?
- What did it actually do?
- Can another app or gate check the receipt later?
- Identity: prove which agent acted, and who is behind it.
- Permission: scoped authority with spending caps, time windows, and revocation — set by you, not guessed by a model.
- Enforcement: gates check the receipt before the action. Out-of-scope attempts are stopped, and the denial is recorded.
- Audit: every pass and denial becomes a receipt other apps, teams, and systems can check later.
- Portability: the same identity, permissions, and receipts follow the agent across tools — including Cursor, Claude Code, and Codex over MCP.
Agent FAQ
Authority, delegation, and trust before automated action.
Ready to add trust?
One OAuth sign-in. The same identity, delegation, and receipts in Cursor, Claude Code, and Codex.