Grantex is an open-source delegated authorization protocol and reference implementation designed specifically for AI agents. It addresses the problem of securely granting AI agents verifiable identities and scoped, time-limited, revocable authority on behalf of humans or organizations. The protocol enables multi-agent delegation, service-side verification, and the creation of attributable audit records, aiming to replace shared or all-or-nothing credentials with mechanisms that support least-privilege access, explicit approval, expiry, delegation constraints, revocation, and auditability.
Grantex is intended for developers and organizations building or deploying autonomous AI agents that require fine-grained authorization and identity management. 0 by reusing familiar authorization concepts such as consent, codes, scopes, and tokens, but extends them with agent identity, multi-agent delegation, and action attribution. The protocol also works alongside MCP, which connects models to tools, by providing proof of which agent may perform which action for a specific principal.
The platform provides SDKs for TypeScript, Python, and Go, each independently versioned, to facilitate integration into various development environments. Notable features include offline consent bundles, on-device verification for Gemma agents, structured consent records, purpose limitation, audit-ready exports, and a public trust registry for AI agent publishers with DID profiles, public keys, and DNS ownership verification. Security capabilities encompass anomaly detection through SQL-backed activity checks and lifecycle APIs, as well as support for custom rule and channel configuration. The tool offers local and network-backed verification of claims and signatures, with options for live revocation checks, and includes middleware for scope enforcement in frameworks such as Express and FastAPI.
0 license and is available as open-source software. 0, with related work published as an individual IETF Internet-Draft. The platform also provides a playground, documentation, and a dashboard for users to explore its features and implementation details.
In the Infrastructure & Backend space, Grantex takes a focused approach. It provides secure, auditable delegated authorization and identity management for AI agents using open standards. It is built as an open-source project for ai infrastructure developers. Grantex is open source under the Apache-2.0 license. It runs on the web, the command line, embeddable surfaces, and API, and it can be self-hosted.
It is developed by Grantex, and the product first shipped in 2026. Development happens publicly on GitHub with 27 stars and 1k commits in the last 90 days. PulseGate's similarity index finds few close equivalents — Grantex occupies a relatively distinct niche. Key capabilities include OAuth 2.0 protocol, agent identity, and verifiable credentials. It exposes integrations via an MCP server and a public API.
Latest indexed changes and source events
grantex.dev discovered by the PulseGate indexer
Other apps tracked under the same category.
