kanoniv/agent-auth
Cryptographic identity and delegation for AI agents
This project helps operations engineers and developers secure the actions of their AI agents. It provides a way to define precisely what an AI agent is allowed to do, such as 'deploy to staging' or 'commit to a specific Git branch.' You give the system a set of allowed actions, and it cryptographically ensures the agent cannot exceed those permissions, producing a clear audit trail of every attempted and successful action.
Available on npm.
Use this if you need to strictly control and audit the real-world operations an AI agent can perform, ensuring it cannot accidentally or maliciously overstep its boundaries, even across different agent systems.
Not ideal if you're looking for a traditional user access management system for human users or if your agents operate in an environment where cryptographic enforcement isn't a primary concern.
Stars
12
Forks
2
Language
TypeScript
License
MIT
Category
Last pushed
Mar 19, 2026
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/kanoniv/agent-auth"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
GetBindu/Bindu
Bindu: Turn any AI agent into a living microservice - interoperable, observable, composable.
opena2a-org/agent-identity-management
AIM - The open-source NHI platform for AI agents. Cryptographic identity, governance, and access control.
peacprotocol/peac
PEAC Protocol: Verifiable interaction records for AI agents and automated systems
openwallet-foundation-labs/sd-jwt-dotnet
Selective Disclosure for JWTs (SD-JWT) .Net implement
vestauth/vestauth
web-bot-auth for agents–from the creator of `dotenv` and `dotenvx`