Security●●●Banger
HumanRoot – Signed proof of human authorization for AI agents
Cryptographic audit trail for agent actions—every delegation traces back to a human.
Big BrainZero to One
thinklanceai
103mo ago
Back to browse
GitHub Repository
Open-source delegated authorization for AI agents — RFC 8693 on-behalf-of tokens, offline-verified constraints, monotonic attenuation. Single Go binary, self-hostable.
0 starsGo
Legant gives AI agents bounded authority to act on your behalf
by baris_erdem·Jun 23, 2026·1 point·0 comments
AI Analysis
●●●BangerBig BrainZero to One
Offline constraint enforcement in tokens beats callback-heavy OAuth alternatives.
Strengths
- •RFC 8693 composite sub/act tokens capture full delegation provenance.
- •Monotonic attenuation prevents authority creep down agent chains.
- •Single Go binary with SDKs for Go, npm, and PyPI ships today.
Weaknesses
- •Zero stars on GitHub means unproven adoption and community support.
- •Niche audience—only matters if you're already building agent systems.
Category
Target Audience
Developers building AI agent systems with bounded authority
Similar To
Keycloak · Ory · Zitadel
Similar Projects
Security●●●Banger
Agentic Power of Attorney (APOA) – An open standard for AI agent auth
Formal auth framework for agentic delegation; fills a gap before agents negotiate house deals.
Big BrainZero to One
juanfiguera
103mo ago
Security●●●Banger
Grantex–Open authorization protocol for AI agents(IETF draft submitted)
OAuth moment for agents—IETF draft submitted, standardizing what's currently API-key chaos.
Zero to OneBig BrainSolve My Problem
mishrasanjeev
203mo ago
Security●●Solid
3 AI agent trust systems cross-verified each other's delegation chains
Delegation chains with accumulating caveats narrow authority at each agent hop.
Big BrainNiche Gem
dreynow
203mo ago
AI/ML●●●Banger
Grantex – Delegated authorization protocol for AI agents
OAuth-equivalent for agents: cryptographic identity, scoped grants, audit trail.
Zero to OneBig Brain
mishrasanjeev
203mo ago
Security●●●Banger
Oath – prove a human authorized each action before your AI agent acts
Cryptographic proof-of-authorization for AI actions; solves real agent oversight problem with clever simplicity.
Big BrainZero to One
danbitengo
123mo ago